Search

Objective: The aim is to detect impacted teeth in panoramic radiology by refining the pretrained MedSAM model. Study design: Impacted teeth are dental issues that can cause complications and are diagnosed via radiographs. We modified SAM model for individual tooth segmentation using 1016 X-ray images. The dataset was split into training, validation, and testing sets, with a ratio of 16:3:1. We enhanced the SAM model to automatically detect impacted teeth by focusing on the tooth's center for more accurate results. Results: With 200 epochs, batch size equals to 1, and a learning rate of 0.001, random images trained the model. Results on the test set showcased performance up to an accuracy of 86.73%, F1-score of 0.5350, and IoU of 0.3652 on SAM-related models. Conclusion: This study fine-tunes MedSAM for impacted tooth segmentation in X-ray images, aiding dental diagnoses. Further improvements on model accuracy and selection are essential for enhancing dental practitioners' diagnostic capabilities. [ABSTRACT FROM AUTHOR]

This study assesses the efficiency of large language models (LLMs) in generating university course structures, comparing traditional methods with Retrieval-Augmented Generation (RAG). It involves a comparative analysis across twelve courses using four LLMs: starling-lm-7b-alpha, openchat_3.5, saiga2_13b, and gpt-3.5-turbo, with four distinct prompting approaches. Findings indicate that advanced prompting techniques significantly influence model performance and response variability. The study underscores the importance of selecting appropriate LLMs and prompting strategies to optimize educational outcomes, highlighting RAG's role in enhancing data retrieval accuracy in educational technology.

In this study, we conducted multi-label annotation based on textual entailment for text data related to incident cases that occurred at an electric power company, utilizing GPT, a general-purpose LLM, without additional training. The experiment examined GPT's zero-shot textual entailment performance and, for comparison, its one-shot textual entailment performance using prompt engineering. Furthermore, in this study, the abstract category labels for the causes of incidents used in the annotation task were also extracted zero-shot from GPT-4, and these were approved by human participants to determine the labels. The results of the experiment showed that, particularly in the one-shot approach using prompt engineering, GPT exhibited strong generalization capabilities and demonstrated promising performance, approaching the level of human annotators in certain evaluation metrics. However, it was also suggested that when dealing with highly specialized and multifaceted cases like those in this study, careful adjustments in model choice and prompt settings are required. [ABSTRACT FROM AUTHOR]

Abstract Zero-shot learning represents a formidable paradigm in machine learning, wherein the crux lies in distilling and generalizing knowledge from observed classes to novel ones. The objective is to identify unfamiliar objects that were not included in the model’s training, leveraging learned patterns and knowledge from previously encountered categories. As a crucial subtask of open-world object detection, zero-shot classification can also provide insights and solutions for this field. Despite its potential, current zero-shot classification models often suffer from a performance gap due to limited transfer ability and discriminative capability of learned representations. In pursuit of advancing the subpar state of zero-shot object classification, this paper introduces a novel model for image classification which can be applied to object detection, namely, self-distillation and k-nearest neighbor-based zero-shot classification method. First, we employ a diffusion detector to identify potential objects in images. Then, self-distillation and distance-based classifiers are used for distinguishing unseen objects from seen classes. The k-nearest neighbor-based cluster heads are designed to cluster the unseen objects. Extensive experiments and visualizations were conducted on publicly available datasets on the efficacy of the proposed approach. Precisely, our model demonstrates performance improvement of over 20% compared to contrastive clustering. Moreover, it achieves a precision of 0.910 and a recall of 0.842 on CIFAR-10 datasets, a precision of 0.737, and a recall of 0.688 on CIFAR-100 datasets for the macro average. Compared to a more recent model (SGFR), our model realized improvements of 10.9%, 13.3%, and 7.8% in Sacc, Uacc, and H metrics, respectively. This study aims to introduce fresh ideas into the domain of zero-shot image classification, and it can be applied to open-world object detection tasks. Our code is available at https://www.github.com/CmosWolf1/Code_implementation_for_paper_SKZC .

Zero-shot learning represents a formidable paradigm in machine learning, wherein the crux lies in distilling and generalizing knowledge from observed classes to novel ones. The objective is to identify unfamiliar objects that were not included in the model's training, leveraging learned patterns and knowledge from previously encountered categories. As a crucial subtask of open-world object detection, zero-shot classification can also provide insights and solutions for this field. Despite its potential, current zero-shot classification models often suffer from a performance gap due to limited transfer ability and discriminative capability of learned representations. In pursuit of advancing the subpar state of zero-shot object classification, this paper introduces a novel model for image classification which can be applied to object detection, namely, self-distillation and k-nearest neighbor-based zero-shot classification method. First, we employ a diffusion detector to identify potential objects in images. Then, self-distillation and distance-based classifiers are used for distinguishing unseen objects from seen classes. The k-nearest neighbor-based cluster heads are designed to cluster the unseen objects. Extensive experiments and visualizations were conducted on publicly available datasets on the efficacy of the proposed approach. Precisely, our model demonstrates performance improvement of over 20% compared to contrastive clustering. Moreover, it achieves a precision of 0.910 and a recall of 0.842 on CIFAR-10 datasets, a precision of 0.737, and a recall of 0.688 on CIFAR-100 datasets for the macro average. Compared to a more recent model (SGFR), our model realized improvements of 10.9%, 13.3%, and 7.8% in Sacc, Uacc, and H metrics, respectively. This study aims to introduce fresh ideas into the domain of zero-shot image classification, and it can be applied to open-world object detection tasks. Our code is available at https://www.github.com/CmosWolf1/Code_implementation_for_paper_SKZC. [ABSTRACT FROM AUTHOR]

Traditional phenotyping relies on experts visually examining plants for physical traits like size, color, or disease presence. Measurements are taken manually using rulers, scales, or color charts, with all data recorded by hand. This labor-intensive and time-consuming process poses a significant obstacle to the efficient breeding of new cultivars. Recent innovations in computer vision and machine learning offer potential solutions for accelerating the development of robust and highly effective plant phenotyping. This study introduces an efficient plant recognition framework that leverages the power of the Segment Anything Model (SAM) guided by Explainable Contrastive Language–Image Pretraining (ECLIP). This approach can be applied to a variety of plant types, eliminating the need for labor-intensive manual phenotyping. To enhance the accuracy of plant phenotype measurements, a B-spline curve is incorporated during the plant component skeleton extraction process. The effectiveness of our approach is demonstrated through experimental results, which show that the proposed framework achieves a mean absolute error (MAE) of less than 0.05 for the majority of test samples. Remarkably, this performance is achieved without the need for model training or labeled data, highlighting the practicality and efficiency of the framework. [ABSTRACT FROM AUTHOR]

The goal of neural architecture search (NAS) is to either downsize the neural architecture and model of a deep neural network (DNN), adjust a neural architecture to improve its end result, or even speed up the whole training process. Such improvements make it possible to generate or install the model of a DNN on a small device, such as a device of internet of things or wireless sensor network. Because most NAS algorithms are time-consuming, finding out a way to reduce their computation costs has now become a critical research issue. The training-free method (also called the zero-shot learning) provides an alternative way to estimate how good a neural architecture is more efficiently during the process of NAS by using a lightweight score function instead of a general training process to avoid incurring heavy costs. This paper starts with a brief discussion of DNN and NAS, followed by a brief review of both model-dependent and model-independent training-free score functions. A brief introduction to the search algorithms and benchmarks that were widely used in a training-free NAS will also be given in this paper. The changes, potential, open issues, and future trends of this research topic are then addressed in the end of this paper.

Super-resolution (SR) of the degraded and real low-resolution (LR) video remains a challenging problem despite the development of deep learning-based SR models. Most existing state-of-the-art networks focus on getting high-resolution (HR) videos from the corresponding down-sampled LR video but fail in scenarios with noisy or degraded low-resolution video. In this article, a novel real-world “zero-shot” video spatio-temporal SR model, i.e., 3D-Deep Convolutional Auto-Encoder (3D-CAE) guided attention-based deep spatio-temporal back-projection network has been proposed. 3D-CAE is utilized for extracting noise-free features from real low-resolution video and used in the attention-based deep spatio-temporal back-projection network for clean, high-resolution video reconstruction. In the proposed framework, the denoising loss of low-resolution video with high-resolution video reconstruction loss is jointly used in an end-to-end manner with a zero-shot setting. Further, Meta-learning is used to initialize the weights of the proposed model to take advantage of learning on the external dataset with internal learning in a zero-shot environment. To maintain the temporal coherency, we have used the Motion Compensation Transformer (MCT) for motion estimation and the Sub-Pixel Motion Compensation (SPMC) layer for motion compensation. We have evaluated the performance of our proposed model on REDS and Vid4 Dataset. The PSNR value of our model is 25.13 dB for the RealVSR dataset, which is 0.72 dB more than the next-best performing model, EAVSR+. For MVSR4x, our model provides 24.61 db PSNR, 0.67 dB more than the EAVSR+ model. Experimental results demonstrate the effectiveness of the proposed framework on degraded and noisy real low-resolution video compared to the existing methods. Furthermore, an ablation study has been conducted to highlight the contribution of 3D-CAE and attention layer to the overall network performance.

This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta's Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies were developed to test SAM's performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than man-made features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrops for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM's applicability in challenging geospatial domains. [ABSTRACT FROM AUTHOR]

Given the large volume of remote sensing images collected daily, automatic object detection and segmentation have been a consistent need in Earth observation (EO). However, objects of interest vary in shape, size, appearance, and reflecting properties. This is not only reflected by the fact that these objects exhibit differences due to their geographical diversity but also by the fact that these objects appear differently in images collected from different sensors (optical and radar) and platforms (satellite, aerial, and unmanned aerial vehicles (UAV)). Although there exists a plethora of object detection methods in the area of remote sensing, given the very fast development of prevalent deep learning methods, there is still a lack of recent updates for object detection methods. In this paper, we aim to provide an update that informs researchers about the recent development of object detection methods and their close sibling in the deep learning era, instance segmentation. The integration of these methods will cover approaches to data at different scales and modalities, such as optical, synthetic aperture radar (SAR) images, and digital surface models (DSM). Specific emphasis will be placed on approaches addressing data and label limitations in this deep learning era. Further, we survey examples of remote sensing applications that benefited from automatic object detection and discuss future trends of the automatic object detection in EO. [ABSTRACT FROM AUTHOR]

With the development of deepfake technology, deepfake detection has received widespread attention. Although some deepfake forensics techniques have been proposed, they are still very difficult to implement in real-world scenarios. This is due to the differences in different deepfake technologies and the compression or editing of videos during the propagation process. Considering the issue of sample imbalance with few-shot scenarios in deepfake detection, we propose a multi-feature channel domain-weighted framework based on meta-learning (MCW). In order to obtain outstanding detection performance of a cross-database, the proposed framework improves a meta-learning network in two ways: it enhances the model's feature extraction ability for detecting targets by combining the RGB domain and frequency domain information of the image and enhances the model's generalization ability for detecting targets by assigning meta weights to channels on the feature map. The proposed MCW framework solves the problems of poor detection performance and insufficient data compression resistance of the algorithm for samples generated by unknown algorithms. The experiment was set in a zero-shot scenario and few-shot scenario, simulating the deepfake detection environment in real situations. We selected nine detection algorithms as comparative algorithms. The experimental results show that the MCW framework outperforms other algorithms in cross-algorithm detection and cross-dataset detection. The MCW framework demonstrates its ability to generalize and resist compression with low-quality training images and across different generation algorithm scenarios, and it has better fine-tuning potential in few-shot learning scenarios. [ABSTRACT FROM AUTHOR]

Recently, the focus of entity linking research has centered on the zero-shot scenario, where the entity purposed to be labeled at the time of testing was never observed during the training phase, or it may belong to a different domain than the source domain. Current studies have used BERT as the base encoder, as it effectively establishes distributional links between source and target domains. The currently available negative sampling methods all use an extractive approach, which makes it difficult for the models to learn diverse and more challenging negative samples. To address this problem, we propose a generative negative sampling method, adaptive_mixup_hard, which generates more difficult negative entities by fusing the features of both positive and negative samples on top of hard negative sampling and introduces a transformable adaptive parameter, W, to increase the diversity of negative samples. Next, we fuse our method with the Biencoder architecture and evaluate its performance under three different score functions. Ultimately, experimental results on the standard benchmark dataset, Zeshel, demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Abstract Most learning-based methods previously used in image dehazing employ a supervised learning strategy, which is time-consuming and requires a large-scale dataset. However, large-scale datasets are difficult to obtain. Here, we propose a self-supervised zero-shot dehazing network (SZDNet) based on dark channel prior, which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the network. Additionally, we use a novel multichannel quad-tree algorithm to estimate atmospheric light values, which is more accurate than previous methods. Furthermore, the sum of the cosine distance and the mean squared error between the pseudo-label and the input image is applied as a loss function to enhance the quality of the dehazed image. The most significant advantage of the SZDNet is that it does not require a large dataset for training before performing the dehazing task. Extensive testing shows promising performances of the proposed method in both qualitative and quantitative evaluations when compared with state-of-the-art methods. Graphical Abstract

Traditional phenotyping relies on experts visually examining plants for physical traits like size, color, or disease presence. Measurements are taken manually using rulers, scales, or color charts, with all data recorded by hand. This labor-intensive and time-consuming process poses a significant obstacle to the efficient breeding of new cultivars. Recent innovations in computer vision and machine learning offer potential solutions for accelerating the development of robust and highly effective plant phenotyping. This study introduces an efficient plant recognition framework that leverages the power of the Segment Anything Model (SAM) guided by Explainable Contrastive Language–Image Pretraining (ECLIP). This approach can be applied to a variety of plant types, eliminating the need for labor-intensive manual phenotyping. To enhance the accuracy of plant phenotype measurements, a B-spline curve is incorporated during the plant component skeleton extraction process. The effectiveness of our approach is demonstrated through experimental results, which show that the proposed framework achieves a mean absolute error (MAE) of less than 0.05 for the majority of test samples. Remarkably, this performance is achieved without the need for model training or labeled data, highlighting the practicality and efficiency of the framework.

Photographs taken under harsh ambient lighting can suffer from a number of image quality degradation phenomena due to insufficient exposure. These include reduced brightness, loss of transfer information, noise, and color distortion. In order to solve the above problems, researchers have proposed many deep learning-based methods to improve the illumination of images. However, most existing methods face the problem of difficulty in obtaining paired training data. In this context, a zero-reference image enhancement network for low light conditions is proposed in this paper. First, the improved Encoder-Decoder structure is used to extract image features to generate feature maps and generate the parameter matrix of the enhancement factor from the feature maps. Then, the enhancement curve is constructed using the parameter matrix. The image is iteratively enhanced using the enhancement curve and the enhancement parameters. Second, the unsupervised algorithm needs to design an image non-reference loss function in training. Four non-reference loss functions are introduced to train the parameter estimation network. Experiments on several datasets with only low-light images show that the proposed network has improved performance compared with other methods in NIQE, PIQE, and BRISQUE non-reference evaluation index, and ablation experiments are carried out for key parts, which proves the effectiveness of this method. At the same time, the performance data of the method on PC devices and mobile devices are investigated, and the experimental analysis is given. This proves the feasibility of the method in this paper in practical application. [ABSTRACT FROM AUTHOR]

The ability of humans to quickly identify general conceptsfrom a handful of images has proven difficult to emulate withrobots. Recently, a computer architecture was developed thatallows robots to mimic some aspects of this human ability bymodeling concepts as cognitive programs using an instructionset of primitive cognitive functions. This allowed a robot toemulate human imagination by simulating candidate programsin a world model before generalizing to the physical world.However, this model used a naive search algorithm that re-quired 30 minutes to discover a single concept, and becameintractable for programs with more than 20 instructions. Tocircumvents this bottleneck, we present an algorithm that emu-lates the human cognitive heuristics of object factorization andsub-goaling, allowing human-level inference speed, improvingaccuracy, and making the output more explainable.

The novelty of zero-shot text classification can address the fundamental challenge of the lack of labeled training data. With the current plethora of multidisciplinary, unstandardized text data, scalable classification models favor unsupervised methods over their supervised counterparts. Overall, the aim is to automate the labelling of each sentence in an input document consisting of section titles and section text. We propose an end-to-end pipeline that includes a document parser, a text classification model called EntailClass, and finally an evaluator to determine balanced accuracy. The suggested pipeline employs a zero-shot approach to classify text within any desired set of aspects. Moreover, text sentences are paired with their section titles and chronological order is maintained within sentences of the same aspect. The proposed automated, three-step pipeline represents a step towards solving the challenge of text classification without the need for an individual dataset for each aspect. It also offers the potential for seamless integration into existing workflows. This zero-shot, generalizable pipeline has achieved 87.2% accuracy and outperformed other state-of-the-art models when applied to supervisory documents.

Most learning-based methods previously used in image dehazing employ a supervised learning strategy, which is time-consuming and requires a large-scale dataset. However, large-scale datasets are difficult to obtain. Here, we propose a self-supervised zero-shot dehazing network (SZDNet) based on dark channel prior, which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the network. Additionally, we use a novel multichannel quad-tree algorithm to estimate atmospheric light values, which is more accurate than previous methods. Furthermore, the sum of the cosine distance and the mean squared error between the pseudo-label and the input image is applied as a loss function to enhance the quality of the dehazed image. The most significant advantage of the SZDNet is that it does not require a large dataset for training before performing the dehazing task. Extensive testing shows promising performances of the proposed method in both qualitative and quantitative evaluations when compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Zero-shot super-resolution (ZSSR) has generated a lot of interest due to its flexibility in various applications. However, the computational demands of ZSSR make it ineffective when dealing with large-scale low-resolution image sets. To address this issue, we propose a novel meta-learning model. We treat the set of low-resolution images as a collection of ZSSR tasks and learn meta-knowledge about ZSSR by leveraging these tasks. This approach reduces the computational burden of super-resolution for large-scale low-resolution images. Additionally, through multiple ZSSR task learning, we uncover a general super-resolution model that enhances the generalization capacity of ZSSR. Finally, using the learned meta-knowledge, our model achieves impressive results with just a few gradient updates when given a novel task. We evaluate our method using two remote sensing datasets with varying spatial resolutions. Our experimental results demonstrate that using multiple ZSSR tasks yields better outcomes than a single task, and our method outperforms other state-of-the-art super-resolution methods. [ABSTRACT FROM AUTHOR]

Copyright of Tourism & Management Studies is the property of Escola Superior de Gestao, Hotelaria e Turismo, Universidade do Algarve and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Although low-resource relation extraction is vital in knowledge construction and characterization, more research is needed on the generalization of unknown relation types. To fill the gap in the study of low-resource (Uyghur) relation extraction methods, we created a zero-shot with a quick relation extraction task setup. Each triplet extracted from an input phrase consists of the subject, relation type, and object. This paper suggests generating structured texts by urging language models to provide related instances. Our model consists of two modules: relation generator and relation and triplet extractor. We use the Uyghur relation prompt in the relation generator stage to generate new synthetic data. In the relation and triple extraction stage, we use the new data to extract the relation triplets in the sentence. We use multi-language model prompts and structured text techniques to offer a structured relation prompt template. This method is the first research that extends relation triplet extraction to a zero-shot setting for Uyghur datasets. Experimental results show that our method achieves a maximum weighted average F1 score of 47.39%. [ABSTRACT FROM AUTHOR]

This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta’s Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies were developed to test SAM’s performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than man-made features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrops for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM’s applicability in challenging geospatial domains.

In zero-shot relation extraction, existing methods usually learn semantic features from seen relations to infer unseen relations. However, because there is no instance of unseen relation that can be used for training, it is still a challenge for the existing models to learn the semantic gap between seen relations and unseen relations, resulting in poor generalization performance of the learned semantic features. Therefore, we propose a Semantic Max-Divergence Metric (SMDM) based method to measure the distances between relations from both direct and indirect semantic differences. For that, we learn multiple binary feature reference-spaces to extract the semantic divergences of each unseen relation instance relative to each seen relation, which can be converted to a relative-affinity (RA) matrix as indirect semantic metrics. Furthermore, we combine RA with direct semantic metrics based on BERT to maximum the divergences between unseen relation instances and get clearer unseen relation boundaries. Empirical results on benchmark datasets demonstrate SMDM can the superior improvement on F1-score and external indicators of SMDM compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The novelty of zero-shot text classification can address the fundamental challenge of the lack of labeled training data. With the current plethora of multidisciplinary, unstandardized text data, scalable classification models favor unsupervised methods over their supervised counterparts. Overall, the aim is to automate the labelling of each sentence in an input document consisting of section titles and section text. We propose an end-to-end pipeline that includes a document parser, a text classification model called EntailClass, and finally an evaluator to determine balanced accuracy. The suggested pipeline employs a zero-shot approach to classify text within any desired set of aspects. Moreover, text sentences are paired with their section titles and chronological order is maintained within sentences of the same aspect. The proposed automated, three-step pipeline represents a step towards solving the challenge of text classification without the need for an individual dataset for each aspect. It also offers the potential for seamless integration into existing workflows. This zero-shot, generalizable pipeline has achieved 87.2% accuracy and outperformed other state-of-the-art models when applied to supervisory documents. [ABSTRACT FROM AUTHOR]

Automatic video understanding is a crucial piece of technology which promotes urban sustainability. Video grounding is a fundamental component of video understanding that has been evolving quickly in recent years, but its use is restricted due to the high labeling costs and typical performance limitations imposed by the pre-defined training dataset. In this paper, a novel atom-based zero-shot video grounding (AZVG) method is proposed to retrieve the segments in the video that correspond to a given input sentence. Although it is training-free, the performance of AZVG is competitive to the weakly supervised methods and better than unsupervised SOTA methods on the Charades-STA dataset. The method can support flexible queries as well as different video content. It can play an important role in a wider range of urban living applications. [ABSTRACT FROM AUTHOR]

Existing counting models predominantly operate on a specific category of objects, such as crowds and vehicles. The recent emergence of multi-modal foundational models, e.g. , Contrastive Language-Image Pre-training (CLIP), has facilitated class-agnostic counting. This involves counting objects of any given class from a single image based on textual instructions. However, CLIP-based class-agnostic counting models face two primary challenges. Firstly, the CLIP model lacks sensitivity to location information. It generally considers global content rather than the fine-grain location of objects. Therefore, adapting the CLIP model directly is suboptimal. Secondly, these models generally freeze pre-trained vision and language encoders, while neglecting the potential misalignment in the constructed hypothesis space. In this paper, we address these two issues in a unified framework termed Deep Spatial Prior Interaction (DSPI) network. The DSPI leverages the spatial-awareness ability of large-scale pre-trained object grounding models, i.e., Grounding DINO, to incorporate spatial location as an additional prior for a specific query class. This enables the network to be more specifically focused on the precise location of the objects. Additionally, to align the feature space across different modalities, we tailor a meta adapter that extracts textual information into an object query. This serves as an instruction for cross-modality matching. These two modules collaboratively ensure the alignment of multi-modal representations while preserving their discriminative nature. Comprehensive experiments conducted on a diverse set of benchmarks verify the superiority of the proposed model. The code is available at https://github.com/jinyongch/DSPI. • Integrate pre-trained multi-modal grounding model for spatial priors to enhance the attentiveness of vision encoder to specific object regions. • Tackle the misalignment issue between textual instructions and visual representations using the designed meta adapter to extract instructive descriptors from the text and transform them into an object query. • Demonstrate that DSPI model can extract distinctive representations aligned across various modalities, while also incorporating precise spatial information, to improve the generalization capability of counting model. [ABSTRACT FROM AUTHOR]

Contrastive Language-Image Pretraining (CLIP) models have achieved significant success and have markedly improved the performance of various downstream tasks, including action recognition. However, how to effectively introduce knowledge into the field of action recognition remains an open question. In this work, an External and Priori Knowledge CLIP (EPK-CLIP) is proposed to introduce external knowledge into the model. To capture external knowledge, an external knowledge embedding module is proposed, which can generate and utilize human-object interaction relations as external knowledge, enabling the model to learn better features. Furthermore, the sparse regularization is introduced in the loss function, endowing the model with the ability to exploit the sparse priori knowledge inherent in the classification task. Finally, multiple inference module is proposed to obtain classification results from both direct and indirect perspectives. Specifically, the final classification result is obtained by fusing the outputs of different reasoning modules. Moreover, four external knowledge datasets: Kinetics-400-VC, Jester-VC, HMDB-51-VC, and UCF-101-VC are built and released for public usage, which is a multimodal extension of corresponding action datasets respectively. Under fully-supervised settings, our model achieves the top-1 accuracy of 84.3%, 97.1%, 82.9%, and 98.2% on Kinetics-400, Jester, HMDB-51, and UCF-101, respectively. In zero-shot experiments, our model also achieves state-of-the-art results, with top-1 accuracy of 51.6% and 77.7% on HMDB-51 and UCF-101, respectively. All related datasets and code can be found at https://github.com/geek12138/EPK-CLIP. • Build video descriptions as external knowledge and inject it into the model. • Embedding sparse priori knowledge reduces the search range of optimal solutions. • Reasoning from different angles to make the model stronger and more stable. • Build and publish four external knowledge datasets. [ABSTRACT FROM AUTHOR]

Image segmentation is one of the most classical computer vision tasks. Segmentation tasks yield a set of classes attributed to individual pixels instead of sparsely predicted images or patches, such as in classification or detection tasks. However, creating annotation sets for pixelwise tasks is a very costly task, often requiring hours for labeling single samples in images with multiple classes of objects. In this context, unsupervised learning can be leveraged either to expedite the annotation procedure and/or to guide the segmentation algorithms altogether without the need for manual annotations. Classical unsupervised segmentation methods leveraged techniques from areas as graph theory, image processing, clustering or supervised classifiers in order to achieve "shallow" pixelwise classification. These techniques usually aim to achieve superpixel over-segmentations by grouping similar pixels that should pertain to the same object. Modern deep unsupervised approaches for image segmentation aimed to group pixels in a data-driven way by using the capabilities of deep architectures to process unstructured data such as images. Later, self-supervised learning bypassed the need for labels via pretext tasks, compelling deep architectures to learn more generic features capable of enhancing downstream tasks, including segmentation. The generalized representations produced by unsupervised models have propelled the recent progress in self-supervised, few- and zero-shot learning and even general-purpose foundational models in computer vision, yielding state-of-the-art results across diverse tasks and datasets. This paper provides an overview of unsupervised and generalizable approaches for image segmentation, introduces key concepts and terminology, and discusses the main aspects of state-of-the-art methods. Additionally, we highlight prominent applications in various domains such as remote sensing, medical imaging, and geology. Finally, we discuss trends and future directions for state-of-the-art unsupervised image segmentation. [Display omitted] [ABSTRACT FROM AUTHOR]

With the development of deepfake technology, deepfake detection has received widespread attention. Although some deepfake forensics techniques have been proposed, they are still very difficult to implement in real-world scenarios. This is due to the differences in different deepfake technologies and the compression or editing of videos during the propagation process. Considering the issue of sample imbalance with few-shot scenarios in deepfake detection, we propose a multi-feature channel domain-weighted framework based on meta-learning (MCW). In order to obtain outstanding detection performance of a cross-database, the proposed framework improves a meta-learning network in two ways: it enhances the model’s feature extraction ability for detecting targets by combining the RGB domain and frequency domain information of the image and enhances the model’s generalization ability for detecting targets by assigning meta weights to channels on the feature map. The proposed MCW framework solves the problems of poor detection performance and insufficient data compression resistance of the algorithm for samples generated by unknown algorithms. The experiment was set in a zero-shot scenario and few-shot scenario, simulating the deepfake detection environment in real situations. We selected nine detection algorithms as comparative algorithms. The experimental results show that the MCW framework outperforms other algorithms in cross-algorithm detection and cross-dataset detection. The MCW framework demonstrates its ability to generalize and resist compression with low-quality training images and across different generation algorithm scenarios, and it has better fine-tuning potential in few-shot learning scenarios.

Recently, the focus of entity linking research has centered on the zero-shot scenario, where the entity purposed to be labeled at the time of testing was never observed during the training phase, or it may belong to a different domain than the source domain. Current studies have used BERT as the base encoder, as it effectively establishes distributional links between source and target domains. The currently available negative sampling methods all use an extractive approach, which makes it difficult for the models to learn diverse and more challenging negative samples. To address this problem, we propose a generative negative sampling method, adaptive_mixup_hard, which generates more difficult negative entities by fusing the features of both positive and negative samples on top of hard negative sampling and introduces a transformable adaptive parameter, W, to increase the diversity of negative samples. Next, we fuse our method with the Biencoder architecture and evaluate its performance under three different score functions. Ultimately, experimental results on the standard benchmark dataset, Zeshel, demonstrate the effectiveness of our method.

In recent years, multilingual question answering has been an emergent research topic and has attracted much attention. Although systems for English and other rich-resource languages that rely on various advanced deep learning-based techniques have been highly developed, most of them in low-resource languages are impractical due to data insufficiency. Accordingly, many studies have attempted to improve the performance of low-resource languages in a zero-shot or few-shot manner based on multilingual bidirectional encoder representations from transformers (mBERT) by transferring knowledge learned from rich-resource languages to low-resource languages. Most methods require either a large amount of unlabeled data or a small set of labeled data for low-resource languages. In Wikipedia, 169 languages have less than 10,000 articles, and 48 languages have less than 1,000 articles. This reason motivates us to conduct a zero-shot multilingual question answering task under a zero-resource scenario. Thus, this study proposes a framework to fine-tune the original mBERT using data from rich-resource languages, and the resulting model can be used for low-resource languages in a zero-shot and zero-resource manner. Compared to several baseline systems, which require millions of unlabeled data for low-resource languages, the performance of our proposed framework is not only highly comparative but is also better for languages used in training.

Recently deep neural networks (DNNs) have achieved tremendous success for object detection in overhead (e.g., satellite) imagery. One ongoing challenge however is the acquisition of training data, due to high costs of obtaining satellite imagery and annotating objects in it. In this article, we present a simple approach—termed Synthetic object IMPLantation (SIMPL)—to easily and rapidly generate large quantities of synthetic overhead training data for custom target objects. We demonstrate the effectiveness of using SIMPL synthetic imagery for training DNNs in zero-shot scenarios where no real imagery is available; and few-shot learning scenarios, where limited real-world imagery is available. We also conduct experiments to study the sensitivity of SIMPL's effectiveness to some key design parameters, providing users for insights when designing synthetic imagery for custom objects. We release a software implementation of our SIMPL approach, as well as design details of our experimental synthetic imagery, so that others can build upon our approach, or use it for their own custom problems.

A major challenge in stance detection is the large (potentially infinite) and diverse set of stance topics. Collecting data for such a set is unrealistic due to both the expense of annotation and the continuous creation of new real-world topics (e.g., a new politician runs for office). Furthermore, stancetaking occurs in a wide range of languages and genres (e.g., Twitter, news articles). While zero-shot stance detection in English, where evaluation is on topics not seen during training, has received increasing attention, we argue that this attention should be expanded to multilingual and multi-genre settings. We discuss two paradigms for English zero-shot stance detection evaluation, as well as recent work in this area. We then discuss recent work on multilingual and multi-genre stance detection, which has focused primarily on non-zero-shot settings. We argue that this work should be expanded to multilingual and multi-genre zero-shot stance detection and propose best practices to systematize and stimulate future work in this direction. While domain adaptation techniques are well-suited for work in these settings, we argue that increased care should be taken to improve model explainability and to conduct robust evaluations, considering not only empirical generalization ability but also the understanding of complex language and inferences.

Aspect-based summarization differs from generic text-summarization in which the generated summary must be conditioned on a given topic. A fundamental challenge to the aspect-based summarization approach is the lack of labeled data for training models, which limits the usage of supervised methods. One approach to address this issue is to introduce human intervention to generate unique datasets per aspect. However, there is a large number of possible aspects to summarize which makes this option impossible to scale. This limits the use of typical modeling techniques, and requires methods which excel in few-shot, or ideally zero-shot regimes. Hence, in this research, we propose a modular, two-step approach that does not need any aspect-based supervision. This research combines recent advances in zero-shot text classification and generic summarization in a novel way. The backbone of the proposed approach is a transformer network trained for the task of textual entailment, which is used to reduce a document to the set of on topic sentences. In the experiments, our model achieves a new state of the art compared to other unsupervised models on the MA-News dataset (ROUGE-1 35.70 and ROUGE-2 15.52), and even outperforms fine-tuned models without any supervision of its own. [ABSTRACT FROM AUTHOR]

Topic classification is the task of mapping text onto a set of meaningful labels known beforehand. This scenario is very common both in academia and industry whenever there is the need of categorizing a big corpus of documents according to set custom labels. The standard supervised approach, however, requires thousands of documents to be manually labelled, and additional effort every time the label taxonomy changes. To obviate these downsides, we investigated the application of a zero-shot approach to topic classification. In this setting, a subset of these topics, or even all of them, is not seen at training time, challenging the model to classify corresponding examples using additional information. We first show how zero-shot classification can perform the topic-classification task without any supervision. Secondly, we build a novel hazard-detection dataset by manually selecting tweets gathered by LINKS Foundation for this task, where we demonstrate the effectivenes of our cost-free method on a real-world problem. The idea is to leverage a pre-trained text-embedder (MPNet) to map both text and topics into the same semantic vector space where they can be compared. We demonstrate that these semantic spaces are better aligned when their dimension is reduced, keeping only the most useful information. We investigated three different dimensionality reduction techniques, namely, linear projection, autoencoding and PCA. Using the macro F1-score as the standard metric, it was found that PCA is the best performing technique, recording improvements for each dataset in comparison with the performance on the baseline. [ABSTRACT FROM AUTHOR]

Zero-shot multilingual fact-checking, which aims to discover and infer subtle clues from the retrieved relevant evidence to verify the given claim in cross-language and cross-domain scenarios, is crucial for optimizing a free, trusted, wholesome global network environment. Previous works have made enlightening and practical explorations in claim verification, while the zero-shot multilingual task faces new challenging gap issues: neglecting authenticity-dependent learning between multilingual claims, lacking heuristic checking, and a bottleneck of insufficient evidence. To alleviate these gaps, a novel Joint Prompt and Evidence Inference Network (PEINet) is proposed to verify the multilingual claim according to the human fact-checking cognitive paradigm. In detail, firstly, we leverage the language family encoding mechanism to strengthen knowledge transfer among multi-language claims. Then, the prompt turning module is designed to infer the falsity of the fact, and further, sufficient fine-grained evidence is extracted and aggregated based on a recursive graph attention network to verify the claim again. Finally, we build a unified inference framework via multi-task learning for final fact verification. The newly achieved state-of-the-art performance on the released challenging benchmark dataset that includes not only an out-of-domain test, but also a zero-shot test, proves the effectiveness of our framework, and further analysis demonstrates the superiority of our PEINet in multilingual claim verification and inference, especially in the zero-shot scenario. [ABSTRACT FROM AUTHOR]

Photographs taken under harsh ambient lighting can suffer from a number of image quality degradation phenomena due to insufficient exposure. These include reduced brightness, loss of transfer information, noise, and color distortion. In order to solve the above problems, researchers have proposed many deep learning-based methods to improve the illumination of images. However, most existing methods face the problem of difficulty in obtaining paired training data. In this context, a zero-reference image enhancement network for low light conditions is proposed in this paper. First, the improved Encoder-Decoder structure is used to extract image features to generate feature maps and generate the parameter matrix of the enhancement factor from the feature maps. Then, the enhancement curve is constructed using the parameter matrix. The image is iteratively enhanced using the enhancement curve and the enhancement parameters. Second, the unsupervised algorithm needs to design an image non-reference loss function in training. Four non-reference loss functions are introduced to train the parameter estimation network. Experiments on several datasets with only low-light images show that the proposed network has improved performance compared with other methods in NIQE, PIQE, and BRISQUE non-reference evaluation index, and ablation experiments are carried out for key parts, which proves the effectiveness of this method. At the same time, the performance data of the method on PC devices and mobile devices are investigated, and the experimental analysis is given. This proves the feasibility of the method in this paper in practical application.

Domain Adaptation aims at adapting the knowledge learned from a domain (source-domain) to another (target-domain). Existing approaches typically require a portion of task-relevant target-domain data a priori. We propose an approach, zero-shot deep domain adaptation (ZDDA), which uses paired dual-domain task-irrelevant data to eliminate the need for task-relevant target-domain training data. ZDDA learns to generate common representations for source and target domains data. Then, either domain representation is used later to train a system that works on both domains or having the ability to eliminate the need to either domain in sensor fusion settings. Two variants of ZDDA have been developed: ZDDA for classification task (ZDDA-C) and ZDDA for metric learning task (ZDDA-ML). Another limitation in Existing approaches is that most of them are designed for the closed-set classification task, i.e., the sets of classes in both the source and target domains are “known.” However, ZDDA-C is also applicable to the open-set classification task where not all classes are “known” during training. Moreover, the effectiveness of ZDDA-ML shows ZDDA’s applicability is not limited to classification tasks. ZDDA-C and ZDDA-ML are tested on classification and metric-learning tasks, respectively. Under most experimental conditions, ZDDA outperforms the baseline without using task-relevant target-domain-training data. [ABSTRACT FROM AUTHOR]

Compact hash codes can facilitate large-scale multimedia retrieval, significantly reducing storage and computation. Most hashing methods learn hash functions based on the data similarity matrix, which is predefined by supervised labels or a distance metric type. However, this predefined similarity matrix cannot accurately reflect the real similarity relationship among images, which results in poor retrieval performance of hashing methods, especially in multi-label datasets and zero-shot datasets that are highly dependent on similarity relationships. Toward this end, this study proposes a new supervised hashing method called supervised adaptive similarity matrix hashing (SASH) via feature-label space consistency. SASH not only learns the similarity matrix adaptively, but also extracts the label correlations by maintaining consistency between the feature and the label space. This correlation information is then used to optimize the similarity matrix. The experiments on three large normal benchmark datasets (including two multi-label datasets) and three large zero-shot benchmark datasets show that SASH has an excellent performance compared with several state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Manually annotating fine-grained slot-value labels for task-oriented dialogue (ToD) systems is an expensive and time-consuming endeavour. This motivates research into slot-filling methods that operate with limited amounts of labelled data. Moreover, the majority of current work on ToD is based solely on text as the input modality, neglecting the additional challenges of imperfect automatic speech recognition (ASR) when working with spoken language. In this work, we propose a Knowledge-Aware Audio-Grounded generative slot filling framework, termed KA2G, that focuses on few-shot and zero-shot slot filling for ToD with speech input. KA2G achieves robust and data-efficient slot filling for speech-based ToD by (1) framing it as a text generation task, (2) grounding text generation additionally in the audio modality, and (3) conditioning on available external knowledge (e.g. a predefined list of possible slot values). We show that combining both modalities within the KA2G framework improves the robustness against ASR errors. Further, the knowledge-aware slot-value generator in KA2G, implemented via a pointer generator mechanism, particularly benefits few-shot and zero-shot learning. Experiments, conducted on the standard speech-based single-turn SLURP dataset and a multi-turn dataset extracted from a commercial ToD system, display strong and consistent gains over prior work, especially in few-shot and zero-shot setups. • A knowledge-aware audio-grounded (KA2G) generative slot-filling framework is proposed • KA2G integrates knowledge with two tree-constrained pointer generator (TCPGen) • 4.6% and 11.2% SLU-F1 increases achieved for rare and unseen entities respectively. • KA2G achieved 20% joint goal accuracy (JGA) improvements on multi-turn dialogue. • The importance of the two TCPGen components were verified via comprehensive analyses [ABSTRACT FROM AUTHOR]

The verbalizer, which serves to map label words to class labels, is an essential component of prompt-tuning. In this paper, we present a novel approach to constructing verbalizers. While existing methods for verbalizer construction mainly rely on augmenting and refining sets of synonyms or related words based on class names, this paradigm suffers from a narrow perspective and lack of abstraction, resulting in limited coverage and high bias in the label-word space. To address this issue, we propose a label-word construction process that incorporates scenario-specific concepts. Specifically, we extract rich concepts from task-specific scenarios as label-word candidates and then develop a novel cascade calibration module to refine the candidates into a set of label words for each class. We evaluate the effectiveness of our proposed approach through extensive experiments on five widely used datasets for zero-shot text classification. The results demonstrate that our method outperforms existing methods and achieves state-of-the-art results. • Retrieving scenario-specific concepts as label word candidates. • Proposing a novel class-name-free cascade approach for label-word refining. • Constructing a verbalizer that has wide-ranging coverage and minimal bias. • Reporting fresh state-of-the-art results. [ABSTRACT FROM AUTHOR]

With new social media concepts emerging, zero-shot cross-modal retrieval methods have gained significant attention. Most of the existing methods assume that the labels of training data are correct and the different modalities are perfectly matched, which is unrealistic in real-life retrieval scenarios. This paper presents a novel approach, termed unpaired robust hashing with noisy labels (URHNL), for zero-shot cross-modal retrieval. Specifically, we developed a zero-shot cross-modal hash retrieval framework that can learn distinct hash codes for different modalities, which is suitable for unpaired cross-modal retrieval scenarios. In addition, it incorporates the sparse constraint on the noise matrix and the low-rank constraint on the recovered label matrix, respectively. These constraints are applied to mitigate the negative effects of noisy labels. Furthermore, we introduce the concept of drag ɛ into the learning process of label semantic embedding, which aims to generate more discriminative hash codes. To improve the similarity of semantic information within hash codes, we consider both intra-modal and inter-modal similarity. A large number of experiments on cross-modal datasets show the effectiveness of the URHNL approach in real and complex zero-shot cross-modal retrieval scenarios. The source code of this word can be found at https://github.com/szq0816/URHNL. [ABSTRACT FROM AUTHOR]

Although existing text classification methods have achieved SOTA results on most tasks, their generalization ability is inferior to their excellent performance on a single task. For this issue, existing research mainly improves the generalization of text classification models by adding label semantics to model training and allowing models to see label semantic information. However, its generalization ability is still limited by the description and quantity of labels. This paper presents a Contrastive Classification method based on contrastive learning to enhance the generalization of text classification models. By transforming all text classification tasks into semantic understanding tasks, the method strengthens the correlation between pre-training tasks and downstream tasks, better preserving the generalization of pre-trained models. At the same time, it unifies the training objectives of all text classification tasks, reducing the differences between different tasks. We verified the model's generalization ability on 17 different zero-shot tasks, verified the model's cross-domain generalization ability and growth potential on 3 question–answer and 2 reading comprehension tasks, and verified the model's performance on 12 supervised text categorization tasks. Experimental results show that Contrastive Classification frees text classification models from the limitations of classification labels and improves them in different dimensions: (1) Robustness, (2) Cross-domain generalization ability, and (3) Growth potential. We plan to release our code at https://github.com/liangyi-qianwan/Contrastive-classification-A-label-independent-generalization-model-for-text-classification/tree/main. [ABSTRACT FROM AUTHOR]

Although low-resource relation extraction is vital in knowledge construction and characterization, more research is needed on the generalization of unknown relation types. To fill the gap in the study of low-resource (Uyghur) relation extraction methods, we created a zero-shot with a quick relation extraction task setup. Each triplet extracted from an input phrase consists of the subject, relation type, and object. This paper suggests generating structured texts by urging language models to provide related instances. Our model consists of two modules: relation generator and relation and triplet extractor. We use the Uyghur relation prompt in the relation generator stage to generate new synthetic data. In the relation and triple extraction stage, we use the new data to extract the relation triplets in the sentence. We use multi-language model prompts and structured text techniques to offer a structured relation prompt template. This method is the first research that extends relation triplet extraction to a zero-shot setting for Uyghur datasets. Experimental results show that our method achieves a maximum weighted average F1 score of 47.39%.

Zero-shot object detection (ZSD) has recently been proposed for detecting objects whose categories have never been seen during training. Existing ZSD works have some drawbacks: (a) the end-to-end methods sacrifice the mean accuracy precision (mAP) on seen classes; (b) the feature-based methods could avoid the above problem but suffer from simple feature construction. Thus, in this paper, we present a succinct but effective feature-based ZSD model whose feature construction naturally leverages the deep feature embedding of the detector itself as the visual features of the detected objects. The features we utilize, named "Detection Feature" (DetFeat), contain not only visual representations but also context and position information, which provide more discriminative information for seen and unseen objects. Additionally, we simulate the construction of the attributes defined by human experts to generate the specific label embedding for the ZSD task, named "Simulated Attributes" (Simu-Attr). We find that Simu-attr promotes better alignment between visual and semantic space for alleviating the problem of the semantic gap. Extensive experiments show that our approach improves the detection performance on unseen classes while maintaining the high detection performance on seen classes. On the challenging COCO dataset, we surpass the best existing transductive ZSD TL-ZSD with about 1% on unseen class and about 10% on seen class using mAP as metric. [ABSTRACT FROM AUTHOR]

Zero-shot super-resolution (ZSSR) has generated a lot of interest due to its flexibility in various applications. However, the computational demands of ZSSR make it ineffective when dealing with large-scale low-resolution image sets. To address this issue, we propose a novel meta-learning model. We treat the set of low-resolution images as a collection of ZSSR tasks and learn meta-knowledge about ZSSR by leveraging these tasks. This approach reduces the computational burden of super-resolution for large-scale low-resolution images. Additionally, through multiple ZSSR task learning, we uncover a general super-resolution model that enhances the generalization capacity of ZSSR. Finally, using the learned meta-knowledge, our model achieves impressive results with just a few gradient updates when given a novel task. We evaluate our method using two remote sensing datasets with varying spatial resolutions. Our experimental results demonstrate that using multiple ZSSR tasks yields better outcomes than a single task, and our method outperforms other state-of-the-art super-resolution methods.

In order to address the scarcity of C-Cr-V-Mo steel samples, a zero-shot transfer component analysis (TCA) based on multi-source is proposed. TCA maps the features of multiple sources composed of different kinds of wear-resistant steels and target domain to the reproducing kernel Hilbert spaces (RKHS). And the proposed fitness parameter $\alpha $ derived from the maximum mean discrepancy (MMD) allows multiple sources to affect the prediction to varying degrees. The support vector regression (SVR) model, established after TCA, can then predict the hardness without homologous samples. The matrix is rapidly predicted by the minimum distance from the sample to the cluster centers of matrix. The (Cr+V)/C, V/Cr and predicted hardness are added to feature space and the abrasion loss of samples quenched at high temperature are predicted using these quenched at low temperature. Experiments show that the multi-source based TCA+SVR model improves the prediction accuracy of hardness of C-Cr-V-Mo steel with R of 0.98 and MAE less than 1.4HRC under zero-shot condition. The primary matrix is quickly identified as martensite. The abrasion loss is mostly effected by hardness, (Cr+V)/C and V/Cr, which is predicted with R of 0.95, MAE of 5.23 mg.

Myoelectric control, the use of electromyogram (EMG) signals generated during muscle contractions to control a system or device, is a promising input, enabling always-available control for emerging ubiquitous computing applications. However, its widespread use has historically been limited by the need for user-specific machine learning models because of behavioural and physiological differences between users. Leveraging the publicly available 612-user EMG-EPN612 dataset, this work dispels this notion, showing that true zero-shot cross-user myoelectric control is achievable without user-specific training. By taking a discrete approach to classification (i.e., recognizing the entire dynamic gesture as a single event), a classification accuracy of 93.0% for six gestures was achieved on a set of 306 unseen users, showing that big data approaches can enable robust cross-user myoelectric control. By organizing the results into a series of mini-studies, this work provides an in-depth analysis of discrete cross-user models to answer unknown questions and uncover new research directions. In particular, this work explores the number of participants required to build cross-user models, the impact of transfer learning for fine-tuning these models, and the effects of under-represented end-user demographics in the training data, among other issues. Additionally, in order to further evaluate the performance of the developed cross-user models, a completely new dataset was created (using the same recording device) that includes known covariate factors such as cross-day use and limb-position variability. The results show that the large data models can effectively generalize to new datasets and mitigate the impact of common confounding factors that have historically limited the adoption of EMG-based inputs., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Eddy, Campbell, Bateman and Scheme.)

Zero-shot learning (ZSL) is one of the most promising avenues of annotation-efficient machine learning. In the era of deep learning, ZSL techniques have achieved unprecedented success. However, the developments of ZSL methods have taken place mostly for natural images. ZSL for medical images has remained largely unexplored. We design a novel strategy for generalized zero-shot diagnosis of chest radiographs. In doing so, we leverage the potential of multi-view semantic embedding, a useful yet less-explored direction for ZSL. Our design also incorporates a self-training phase to tackle the problem of noisy labels alongside improving the performance for classes not seen during training. Through rigorous experiments, we show that our model trained on one dataset can produce consistent performance across test datasets from different sources including those with very different quality. Comparisons with a number of state-of-the-art techniques show the superiority of the proposed method for generalized zero-shot chest x-ray diagnosis. [ABSTRACT FROM AUTHOR]