Search

Automatic polyp segmentation is crucial for effective diagnosis and treatment in colonoscopy images. Traditional methods encounter significant challenges in accurately delineating polyps due to limitations in feature representation and the handling of variability in polyp appearance. Deep learning techniques, including CNN and Transformer-based methods, have been explored to improve polyp segmentation accuracy. However, existing approaches often neglect additional semantics, restricting their ability to acquire adequate contexts of polyps in colonoscopy images. In this paper, we propose an innovative method named ``Automatic Polyp Segmentation with Self-Enriched Semantic Model'' to address these limitations. First, we extract a sequence of features from an input image and decode high-level features to generate an initial segmentation mask. Using the proposed self-enriched semantic module, we query potential semantics and augment deep features with additional semantics, thereby aiding the model in understanding context more effectively. Extensive experiments show superior segmentation performance of the proposed method against state-of-the-art polyp segmentation baselines across five polyp benchmarks in both superior learning and generalization capabilities., Comment: Asian Conference on Computer Vision 2024

With the increased popularity of mobile devices, Web mapping services have become an indispensable tool in our daily lives. To provide user-satisfied services, such as location searches, the point of interest (POI) database is the fundamental infrastructure, as it archives multimodal information on billions of geographic locations closely related to people's lives, such as a shop or a bank. Therefore, verifying the correctness of a large-scale POI database is vital. To achieve this goal, many industrial companies adopt volunteered geographic information (VGI) platforms that enable thousands of crowdworkers and expert mappers to verify POIs seamlessly; but to do so, they have to spend millions of dollars every year. To save the tremendous labor costs, we devised DuMapper, an automatic system for large-scale POI verification with the multimodal street-view data at Baidu Maps. DuMapper takes the signboard image and the coordinates of a real-world place as input to generate a low-dimensional vector, which can be leveraged by ANN algorithms to conduct a more accurate search through billions of archived POIs in the database for verification within milliseconds. It can significantly increase the throughput of POI verification by $50$ times. DuMapper has already been deployed in production since \DuMPOnline, which dramatically improves the productivity and efficiency of POI verification at Baidu Maps. As of December 31, 2021, it has enacted over $405$ million iterations of POI verification within a 3.5-year period, representing an approximate workload of $800$ high-performance expert mappers.

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improving ASR performance., Comment: Accepted by the 6th IEEE International Conference on Image Processing Applications and Systems

Every year, thousands of people suffer from skull damage and require personalized implants to fill the cranial cavity. Unfortunately, the waiting time for reconstruction surgery can extend to several weeks or even months, especially in less developed countries. One factor contributing to the extended waiting period is the intricate process of personalized implant modeling. Currently, the preparation of these implants by experienced biomechanical experts is both costly and time-consuming. Recent advances in artificial intelligence, especially in deep learning, offer promising potential for automating the process. However, deep learning-based cranial reconstruction faces several challenges: (i) the limited size of training datasets, (ii) the high resolution of the volumetric data, and (iii) significant data heterogeneity. In this work, we propose a novel approach to address these challenges by enhancing the reconstruction through learnable symmetry enforcement. We demonstrate that it is possible to train a neural network dedicated to calculating skull symmetry, which can be utilized either as an additional objective function during training or as a post-reconstruction objective during the refinement step. We quantitatively evaluate the proposed method using open SkullBreak and SkullFix datasets, and qualitatively using real clinical cases. The results indicate that the symmetry-preserving reconstruction network achieves considerably better outcomes compared to the baseline (0.94/0.94/1.31 vs 0.84/0.76/2.43 in terms of DSC, bDSC, and HD95). Moreover, the results are comparable to the best-performing methods while requiring significantly fewer computational resources (< 500 vs > 100,000 GPU hours). The proposed method is a considerable contribution to the field of applied artificial intelligence in medicine and is a step toward automatic cranial defect reconstruction in clinical practice.

Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directly from GitHub, are essential for training machine learning models to detect these security flaws. However, these datasets frequently suffer from significant noise, typically 40% to 75%, due primarily to the automatic and indiscriminate labeling of all changes in vulnerability-fixing commits (VFCs) as vulnerability-related. This misclassification occurs because not all changes in a commit aimed at fixing vulnerabilities pertain to security threats; many are routine updates like bug fixes or test improvements. This paper introduces the first methodology that uses the Large Language Model (LLM) with a heuristic enhancement to automatically identify vulnerability-fixing changes from VFCs, achieving an F1-score of 0.82. VulSifter was applied to a large-scale study, where we conducted a crawl of 127,063 repositories on GitHub, resulting in the acquisition of 5,352,105 commits. VulSifter involves utilizing an LLM to comprehend code semantics and contextual information, while applying heuristics to filter out unrelated changes. We then developed CleanVul, a high-quality dataset comprising 11,632 functions using our LLM heuristic enhancement approach, demonstrating Correctness (90.6%) comparable to established datasets such as SVEN and PrimeVul. To evaluate the CleanVul dataset, we conducted experiments focusing on fine-tuning various LLMs on CleanVul and other high-quality datasets. Evaluation results reveal that LLMs fine-tuned on CleanVul not only exhibit enhanced accuracy but also superior generalization capabilities compared to those trained on uncleaned datasets. Specifically, models trained on CleanVul and tested on PrimeVul achieve accuracy higher than those trained and tested exclusively on PrimeVul.

In recent years, the use of deep learning (DL) methods, including convolutional neural networks (CNNs) and vision transformers (ViTs), has significantly advanced computational pathology, enhancing both diagnostic accuracy and efficiency. Hematoxylin and Eosin (H&E) Whole Slide Images (WSI) plays a crucial role by providing detailed tissue samples for the analysis and training of DL models. However, WSIs often contain regions with artifacts such as tissue folds, blurring, as well as non-tissue regions (background), which can negatively impact DL model performance. These artifacts are diagnostically irrelevant and can lead to inaccurate results. This paper proposes a fully automatic supervised DL pipeline for WSI Quality Assessment (WSI-QA) that uses a fused model combining CNNs and ViTs to detect and exclude WSI regions with artifacts, ensuring that only qualified WSI regions are used to build DL-based computational pathology applications. The proposed pipeline employs a pixel-based segmentation model to classify WSI regions as either qualified or non-qualified based on the presence of artifacts. The proposed model was trained on a large and diverse dataset and validated with internal and external data from various human organs, scanners, and H&E staining procedures. Quantitative and qualitative evaluations demonstrate the superiority of the proposed model, which outperforms state-of-the-art methods in WSI artifact detection. The proposed model consistently achieved over 95% accuracy, precision, recall, and F1 score across all artifact types. Furthermore, the WSI-QA pipeline shows strong generalization across different tissue types and scanning conditions., Comment: submitted to IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, November 25, 2024

This paper presents a method for object recognition and automatic labeling in large-area remote sensing images called LRSAA. The method integrates YOLOv11 and MobileNetV3-SSD object detection algorithms through ensemble learning to enhance model performance. Furthermore, it employs Poisson disk sampling segmentation techniques and the EIOU metric to optimize the training and inference processes of segmented images, followed by the integration of results. This approach not only reduces the demand for computational resources but also achieves a good balance between accuracy and speed. The source code for this project has been made publicly available on https://github.com/anaerovane/LRSAA., Comment: arXiv admin note: text overlap with arXiv:2411.07802

Surgical assessment of liver cancer patients requires identification of the vessel trees from medical images. Specifically, the venous trees - the portal (perfusing) and the hepatic (draining) trees are important for understanding the liver anatomy and disease state, and perform surgery planning. This research aims to improve the 3D segmentation, skeletonization, and subsequent analysis of vessel trees, by creating an automatic pipeline based on deep learning and image processing techniques. The first part of this work explores the impact of differentiable skeletonization methods such as ClDice and morphological skeletonization loss, on the overall liver vessel segmentation performance. To this aim, it studies how to improve vessel tree connectivity. The second part of this study converts a single class vessel segmentation into multi-class ones, separating the two venous trees. It builds on the previous two-class vessel segmentation model, which vessel tree outputs might be entangled, and on connected components and skeleton analyses of the trees. After providing sub-labeling of the specific anatomical branches of each venous tree, these algorithms also enable a morphometric analysis of the vessel trees by extracting various geometrical markers. In conclusion, we propose a method that successfully improves current skeletonization methods, for extensive vascular trees that contain vessels of different calibers. The separation algorithm creates a clean multi-class segmentation of the vessels, validated by surgeons to provide low error. A new, publicly shared high-quality liver vessel dataset of 77 cases is thus created. Finally a method to annotate vessel trees according to anatomy is provided, enabling a unique liver vessel morphometry analysis., Comment: Internship at Simbiotx

Quantum networking continues to encode information in polarization states due to ease and precision. The variable environmental polarization transformations induced by deployed fiber need correction for deployed quantum networking. Here we present a new method for automatic polarization compensation (APC) and demonstrate its performance on a metropolitan quantum network. Designing an APC involves many design decisions indicated by the diversity of previous solutions in the literature. Our design leverages heterodyne detection of wavelength-multiplexed dim classical references for continuous high-bandwidth polarization measurements used by newly developed multi-axis (non-)linear control algorithm(s) for complete polarization channel stabilization with no downtime. This enables continuous relatively high-bandwidth correction without significant added noise from classical reference signals. We demonstrate the performance of our APC using a variety of classical and quantum characterizations. Finally, we use C-band and L-band APC versions to demonstrate continuous high-fidelity entanglement distribution on a metropolitan quantum network with average relative fidelity of $0.94\pm0.03$ for over 30 hrs, Comment: 31 pages, 14 figures, 1 table

Relational object invariants (or representation invariants) are relational properties held by the fields of a (memory) object throughout its lifetime. For example, the length of a buffer never exceeds its capacity. Automatic inference of these invariants is particularly challenging because they are often broken temporarily during field updates. In this paper, we present an Abstract Interpretation-based solution to infer object invariants. Our key insight is a new object abstraction for memory objects, where memory is divided into multiple memory banks, each containing several objects. Within each bank, the objects are further abstracted by separating the most recently used (MRU) object, represented precisely with strong updates, while the rest are summarized. For an effective implementation of this approach, we introduce a new composite abstract domain, which forms a reduced product of numerical and equality sub-domains. This design efficiently expresses relationships between a small number of variables (e.g., fields of the same abstract object). We implement the new domain in the CRAB abstract interpreter and evaluate it on several benchmarks for memory safety. We show that our approach is significantly more scalable for relational properties than the existing implementation of CRAB. For evaluating precision, we have integrated our analysis as a pre-processing step to SEABMC bounded model checker, and show that it is effective at both discharging assertions during pre-processing, and significantly improving the run-time of SEABMC., Comment: This is an extended version of the VMCAI 2025 paper, consisting of 26 pages. The artifact is available at https://doi.org/10.5281/zenodo.13849174

The combination of Large Language Models (LLM) and Automatic Speech Recognition (ASR), when deployed on edge devices (called edge ASR-LLM), can serve as a powerful personalized assistant to enable audio-based interaction for users. Compared to text-based interaction, edge ASR-LLM allows accessible and natural audio interactions. Unfortunately, existing ASR-LLM models are mainly trained in high-performance computing environments and produce substantial model weights, making them difficult to deploy on edge devices. More importantly, to better serve users' personalized needs, the ASR-LLM must be able to learn from each distinct user, given that audio input often contains highly personalized characteristics that necessitate personalized on-device training. Since individually fine-tuning the ASR or LLM often leads to suboptimal results due to modality-specific limitations, end-to-end training ensures seamless integration of audio features and language understanding (cross-modal alignment), ultimately enabling a more personalized and efficient adaptation on edge devices. However, due to the complex training requirements and substantial computational demands of existing approaches, cross-modal alignment between ASR audio and LLM can be challenging on edge devices. In this work, we propose a resource-efficient cross-modal alignment framework that bridges ASR and LLMs on edge devices to handle personalized audio input. Our framework enables efficient ASR-LLM alignment on resource-constrained devices like NVIDIA Jetson Orin (8GB RAM), achieving 50x training time speedup while improving the alignment quality by more than 50\%. To the best of our knowledge, this is the first work to study efficient ASR-LLM alignment on resource-constrained edge devices., Comment: 7 pages, 8 figures

Automatic Speech Recognition (ASR) technology has witnessed significant advancements in recent years, revolutionizing human-computer interactions. While major languages have benefited from these developments, lesser-resourced languages like Urdu face unique challenges. This paper provides an extensive exploration of the dynamic landscape of ASR research, focusing particularly on the resource-constrained Urdu language, which is widely spoken across South Asian nations. It outlines current research trends, technological advancements, and potential directions for future studies in Urdu ASR, aiming to pave the way for forthcoming researchers interested in this domain. By leveraging contemporary technologies, analyzing existing datasets, and evaluating effective algorithms and tools, the paper seeks to shed light on the unique challenges and opportunities associated with Urdu language processing and its integration into the broader field of speech research., Comment: Submitted to SN Computer Science

In recent years, terrestrial laser scanning technology has been widely used to collect tree point cloud data, aiding in measurements of diameter at breast height, biomass, and other forestry survey data. Since a single scan from terrestrial laser systems captures data from only one angle, multiple scans must be registered and fused to obtain complete tree point cloud data. This paper proposes a marker-free automatic registration method for single-tree point clouds based on similar tetrahedras. First, two point clouds from two scans of the same tree are used to generate tree skeletons, and key point sets are constructed from these skeletons. Tetrahedra are then filtered and matched according to similarity principles, with the vertices of these two matched tetrahedras selected as matching point pairs, thus completing the coarse registration of the point clouds from the two scans. Subsequently, the ICP method is applied to the coarse-registered leaf point clouds to obtain fine registration parameters, completing the precise registration of the two tree point clouds. Experiments were conducted using terrestrial laser scanning data from eight trees, each from different species and with varying shapes. The proposed method was evaluated using RMSE and Hausdorff distance, compared against the traditional ICP and NDT methods. The experimental results demonstrate that the proposed method significantly outperforms both ICP and NDT in registration accuracy, achieving speeds up to 593 times and 113 times faster than ICP and NDT, respectively. In summary, the proposed method shows good robustness in single-tree point cloud registration, with significant advantages in accuracy and speed compared to traditional ICP and NDT methods, indicating excellent application prospects in practical registration scenarios., Comment: remote sensing; terrestrial lidar; multi-scan cloud registration

The automatic analysis of scores has been a research topic of interest for the last few decades and still is since music databases that include musical scores are currently being created to make musical content available to the public, including scores of ancient music. For the correct analysis of music elements and their interpretation, the identification of staff lines is of key importance. In this paper, a scheme to post-process the output of a previous musical object identification system is described. This system allows the reconstruction by means of detection, tracking and interpolation of the staff lines of ancient scores from the digital Salzinnes Database. The scheme developed shows a remarkable performance on the specific task it was created for., Comment: 15 pages

Behavioral models are incredibly useful for understanding and validating software. However, the automatic extraction of such models from actual industrial code remains a largely unsolved problem with current solutions often not scaling well with the complexity and size of industrial systems or having to rely on approximations. To enable the extraction of useful models from code, we provide a framework for transforming object-oriented code into processes from which, when paired with minimal user input, models can be automatically generated and composed. Paired with this, we introduce the novel SSTraGen (StateSpace Transformation & Generation) tool, which provides an implementation of this framework. Through case studies at Philips Image Guided Therapy Systems, we showcase the practical applicability and usefulness of this tool, including the transformation of a component with >1000 LOC.

This paper presents a data-driven electrical machine design (EMD) framework using wound-rotor synchronous generator (WRSG) as a design example. Unlike traditional preliminary EMD processes that heavily rely on expertise, this framework leverages an artificial-intelligence based expert database, to provide preliminary designs directly from user specifications. Initial data is generated using 2D finite element (FE) machine models by sweeping fundamental design variables including machine length and diameter, enabling scalable machine geometry with machine performance for each design is recorded. This data trains a Metamodel of Optimal Prognosis (MOP)-based surrogate model, which maps design variables to key performance indicators (KPIs). Once trained, guided by metaheuristic algorithms, the surrogate model can generate thousands of geometric scalable designs, covering a wide power range, forming an AI expert database to guide future preliminary design. The framework is validated with a 30kVA WRSG design case. A prebuilt WRSG database, covering power from 10 to 60kVA, is validated by FE simulation. Design No.1138 is selected from database and compared with conventional design. Results show No.1138 achieves a higher power density of 2.21 kVA/kg in just 5 seconds, compared to 2.02 kVA/kg obtained using traditional method, which take several days. The developed AI expert database also serves as a high-quality data source for further developing AI models for automatic electrical machine design.

Summarizing patient clinical notes is vital for reducing documentation burdens. Current manual summarization makes medical staff struggle. We propose an automatic method using LLMs, but long inputs cause LLMs to lose context, reducing output quality especially in small size model. We used a 7B model, open-calm-7b, enhanced with Native Bayes Context Extend and a redesigned decoding mechanism to reference one sentence at a time, keeping inputs within context windows, 2048 tokens. Our improved model achieved near parity with Google's over 175B Gemini on ROUGE-L metrics with 200 samples, indicating strong performance using less resources, enhancing automated EMR summarization feasibility.

Automatic modulation classification (AMC) has emerged as a key technique in cognitive radio networks in sixth-generation (6G) communications. AMC enables effective data transmission without requiring prior knowledge of modulation schemes. However, the low classification accuracy under the condition of low signal-to-noise ratio (SNR) limits the implementation of AMC techniques under the rapidly changing physical channels in 6G and beyond. This paper investigates the AMC technique for the signals with dynamic and varying SNRs, and a deep learning based noise reduction network is proposed to reduce the noise introduced by the wireless channel and the receiving equipment. In particular, a transfer learning guided learning framework (TNR-AMC) is proposed to utilize the scarce annotated modulation signals and improve the classification accuracy for low SNR modulation signals. The numerical results show that the proposed noise reduction network achieves an accuracy improvement of over 20\% in low SNR scenarios, and the TNR-AMC framework can improve the classification accuracy under unstable SNRs., Comment: Submitted to ICC 2025