Search

Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos. Recent works focus on learning the cross-modal alignment between video segments and ASR-transcripted narration texts through contrastive learning. However, these methods fail to account for the alignment noise, i.e., irrelevant narrations to the instructional task in videos and unreliable timestamps in narrations. To address these challenges, this work proposes a novel training framework. Motivated by the strong capabilities of Large Language Models (LLMs) in procedure understanding and text summarization, we first apply an LLM to filter out task-irrelevant information and summarize task-related procedure steps (LLM-steps) from narrations. To further generate reliable pseudo-matching between the LLM-steps and the video for training, we propose the Multi-Pathway Text-Video Alignment (MPTVA) strategy. The key idea is to measure alignment between LLM-steps and videos via multiple pathways, including: (1) step-narration-video alignment using narration timestamps, (2) direct step-to-video alignment based on their long-term semantic similarity, and (3) direct step-to-video alignment focusing on short-term fine-grained semantic similarity learned from general video domains. The results from different pathways are fused to generate reliable pseudo step-video matching. We conducted extensive experiments across various tasks and problem settings to evaluate our proposed method. Our approach surpasses state-of-the-art methods in three downstream tasks: procedure step grounding, step localization, and narration grounding by 5.9\%, 3.1\%, and 2.8\%., Comment: Accepted to ECCV 2024

Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods that enable better alignment between visual encoders and backbone LLMs, concerning MLLM's visual grounding, object referring, and compositional reasoning abilities. In addition, we provide a summary of model training and in-context learning methods to improve MLLM's perception and understanding of visual prompts. This paper examines visual prompting methods developed in MLLMs and provides a vision of the future of these methods., Comment: 10 pages

Large Language Models (LLMs) have significantly enhanced Information Retrieval (IR) across various modules, such as reranking. Despite impressive performance, current zero-shot relevance ranking with LLMs heavily relies on human prompt engineering. Existing automatic prompt engineering algorithms primarily focus on language modeling and classification tasks, leaving the domain of IR, particularly reranking, underexplored. Directly applying current prompt engineering algorithms to relevance ranking is challenging due to the integration of query and long passage pairs in the input, where the ranking complexity surpasses classification tasks. To reduce human effort and unlock the potential of prompt optimization in reranking, we introduce a novel automatic prompt engineering algorithm named APEER. APEER iteratively generates refined prompts through feedback and preference optimization. Extensive experiments with four LLMs and ten datasets demonstrate the substantial performance improvement of APEER over existing state-of-the-art (SoTA) manual prompts. Furthermore, we find that the prompts generated by APEER exhibit better transferability across diverse tasks and LLMs. Code is available at https://github.com/jincan333/APEER.

While diffusion models have significantly advanced the quality of image generation their capability to accurately and coherently render text within these images remains a substantial challenge. Conventional diffusion-based methods for scene text generation are typically limited by their reliance on an intermediate layout output. This dependency often results in a constrained diversity of text styles and fonts an inherent limitation stemming from the deterministic nature of the layout generation phase. To address these challenges this paper introduces SceneTextGen a novel diffusion-based model specifically designed to circumvent the need for a predefined layout stage. By doing so SceneTextGen facilitates a more natural and varied representation of text. The novelty of SceneTextGen lies in its integration of three key components: a character-level encoder for capturing detailed typographic properties coupled with a character-level instance segmentation model and a word-level spotting model to address the issues of unwanted text generation and minor character inaccuracies. We validate the performance of our method by demonstrating improved character recognition rates on generated images across different public visual text datasets in comparison to both standard diffusion based methods and text specific methods., Comment: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 7496-7506

Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. We introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity. Extensive evaluations on text-to-image diffusion models demonstrate SODA's effectiveness, offering a spectrum-aware alternative to existing fine-tuning methods.

In-context Learning (ICL) empowers large language models (LLMs) to adapt to unseen tasks during inference by prefixing a few demonstration examples prior to test queries. Despite its versatility, ICL incurs substantial computational and memory overheads compared to zero-shot learning and is susceptible to the selection and order of demonstration examples. In this work, we introduce Implicit In-context Learning (I2CL), an innovative paradigm that addresses the challenges associated with traditional ICL by absorbing demonstration examples within the activation space. I2CL first generates a condensed vector representation, namely a context vector, from the demonstration examples. It then integrates the context vector during inference by injecting a linear combination of the context vector and query activations into the model's residual streams. Empirical evaluation on nine real-world tasks across three model architectures demonstrates that I2CL achieves few-shot performance with zero-shot cost and exhibits robustness against the variation of demonstration examples. Furthermore, I2CL facilitates a novel representation of "task-ids", enhancing task similarity detection and enabling effective transfer learning. We provide a comprehensive analysis of I2CL, offering deeper insights into its mechanisms and broader implications for ICL. The source code is available at: https://github.com/LzVv123456/I2CL.

Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models. It is, therefore, necessary to analyze the origin of images by inferring if a particular image was generated by a specific latent generative model. Most existing methods (e.g., image watermark and model fingerprinting) require extra steps during training or generation. These requirements restrict their usage on the generated images without such extra operations, and the extra required operations might compromise the quality of the generated images. In this work, we ask whether it is possible to effectively and efficiently trace the images generated by a specific latent generative model without the aforementioned requirements. To study this problem, we design a latent inversion based method called LatentTracer to trace the generated images of the inspected model by checking if the examined images can be well-reconstructed with an inverted latent input. We leverage gradient based latent inversion and identify a encoder-based initialization critical to the success of our approach. Our experiments on the state-of-the-art latent generative models, such as Stable Diffusion, show that our method can distinguish the images generated by the inspected model and other images with a high accuracy and efficiency. Our findings suggest the intriguing possibility that today's latent generative generated images are naturally watermarked by the decoder used in the source models. Code: https://github.com/ZhentingWang/LatentTracer., Comment: ICML 2024

The perception of 3D motion of surrounding traffic participants is crucial for driving safety. While existing works primarily focus on general large motions, we contend that the instantaneous detection and quantification of subtle motions is equally important as they indicate the nuances in driving behavior that may be safety critical, such as behaviors near a stop sign of parking positions. We delve into this under-explored task, examining its unique challenges and developing our solution, accompanied by a carefully designed benchmark. Specifically, due to the lack of correspondences between consecutive frames of sparse Lidar point clouds, static objects might appear to be moving - the so-called swimming effect. This intertwines with the true object motion, thereby posing ambiguity in accurate estimation, especially for subtle motions. To address this, we propose to leverage local occupancy completion of object point clouds to densify the shape cue, and mitigate the impact of swimming artifacts. The occupancy completion is learned in an end-to-end fashion together with the detection of moving objects and the estimation of their motion, instantaneously as soon as objects start to move. Extensive experiments demonstrate superior performance compared to standard 3D motion estimation approaches, particularly highlighting our method's specialized treatment of subtle motions., Comment: CVPR 2024

Cardiac MRI, crucial for evaluating heart structure and function, faces limitations like slow imaging and motion artifacts. Undersampling reconstruction, especially data-driven algorithms, has emerged as a promising solution to accelerate scans and enhance imaging performance using highly under-sampled data. Nevertheless, the scarcity of publicly available cardiac k-space datasets and evaluation platform hinder the development of data-driven reconstruction algorithms. To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th International Conference on MICCAI. CMRxRecon presented an extensive k-space dataset comprising cine and mapping raw data, accompanied by detailed annotations of cardiac anatomical structures. With overwhelming participation, the challenge attracted more than 285 teams and over 600 participants. Among them, 22 teams successfully submitted Docker containers for the testing phase, with 7 teams submitted for both cine and mapping tasks. All teams use deep learning based approaches, indicating that deep learning has predominately become a promising solution for the problem. The first-place winner of both tasks utilizes the E2E-VarNet architecture as backbones. In contrast, U-Net is still the most popular backbone for both multi-coil and single-coil reconstructions. This paper provides a comprehensive overview of the challenge design, presents a summary of the submitted results, reviews the employed methods, and offers an in-depth discussion that aims to inspire future advancements in cardiac MRI reconstruction models. The summary emphasizes the effective strategies observed in Cardiac MRI reconstruction, including backbone architecture, loss function, pre-processing techniques, physical modeling, and model complexity, thereby providing valuable insights for further developments in this field., Comment: 25 pages, 17 figures

Generalization remains a central challenge in machine learning. In this work, we propose Learning from Teaching (LoT), a novel regularization technique for deep neural networks to enhance generalization. Inspired by the human ability to capture concise and abstract patterns, we hypothesize that generalizable correlations are expected to be easier to imitate. LoT operationalizes this concept to improve generalization of the main model with auxiliary student learners. The student learners are trained by the main model and, in turn, provide feedback to help the main model capture more generalizable and imitable correlations. Our experimental results across several domains, including Computer Vision, Natural Language Processing, and methodologies like Reinforcement Learning, demonstrate that the introduction of LoT brings significant benefits compared to training models on the original dataset. The results suggest the effectiveness and efficiency of LoT in identifying generalizable information at the right scales while discarding spurious data correlations, thus making LoT a valuable addition to current machine learning. Code is available at https://github.com/jincan333/LoT.

The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has proven successful, but requires good positive and negative samples. However, the free-form nature and the open vocabulary of object descriptions make the space of negatives extremely large. Prior works randomly sample negatives or use rule-based techniques to build them. In contrast, we propose to leverage the vast knowledge built into modern generative models to automatically build negatives that are more relevant to the original data. Specifically, we use large-language-models to generate negative text descriptions, and text-to-image diffusion models to also generate corresponding negative images. Our experimental analysis confirms the relevance of the generated negative data, and its use in language-based detectors improves performance on two complex benchmarks. Code is available at \url{https://github.com/xiaofeng94/Gen-Enhanced-Negs}., Comment: Accepted to CVPR 2024. The supplementary document included

The key to dynamic or multi-contrast magnetic resonance imaging (MRI) reconstruction lies in exploring inter-frame or inter-contrast information. Currently, the unrolled model, an approach combining iterative MRI reconstruction steps with learnable neural network layers, stands as the best-performing method for MRI reconstruction. However, there are two main limitations to overcome: firstly, the unrolled model structure and GPU memory constraints restrict the capacity of each denoising block in the network, impeding the effective extraction of detailed features for reconstruction; secondly, the existing model lacks the flexibility to adapt to variations in the input, such as different contrasts, resolutions or views, necessitating the training of separate models for each input type, which is inefficient and may lead to insufficient reconstruction. In this paper, we propose a two-stage MRI reconstruction pipeline to address these limitations. The first stage involves filling the missing k-space data, which we approach as a physics-based reconstruction problem. We first propose a simple yet efficient baseline model, which utilizes adjacent frames/contrasts and channel attention to capture the inherent inter-frame/-contrast correlation. Then, we extend the baseline model to a prompt-based learning approach, PromptMR, for all-in-one MRI reconstruction from different views, contrasts, adjacent types, and acceleration factors. The second stage is to refine the reconstruction from the first stage, which we treat as a general video restoration problem to further fuse features from neighboring frames/contrasts in the image domain. Extensive experiments show that our proposed method significantly outperforms previous state-of-the-art accelerated MRI reconstruction methods., Comment: STACOM 2023; Code is available at https://github.com/hellopipu/PromptMR

Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising results. However, these methods either use a relatively large number of primitives or lack geometric flexibility due to the limited expressibility of the primitives. In this paper, we propose a novel bi-channel Transformer architecture, integrated with parameterized deformable models, termed DeFormer, to simultaneously estimate the global and local deformations of primitives. In this way, DeFormer can abstract complex object shapes while using a small number of primitives which offer a broader geometry coverage and finer details. Then, we introduce a force-driven dynamic fitting and a cycle-consistent re-projection loss to optimize the primitive parameters. Extensive experiments on ShapeNet across various settings show that DeFormer achieves better reconstruction accuracy over the state-of-the-art, and visualizes with consistent semantic correspondences for improved interpretability., Comment: Accepted by ICCV 2023

The task of shape abstraction with semantic part consistency is challenging due to the complex geometries of natural objects. Recent methods learn to represent an object shape using a set of simple primitives to fit the target. \textcolor{black}{However, in these methods, the primitives used do not always correspond to real parts or lack geometric flexibility for semantic interpretation.} In this paper, we investigate salient and efficient primitive descriptors for accurate shape abstractions, and propose \textit{Deep Deformable Models (DDMs)}. DDM employs global deformations and diffeomorphic local deformations. These properties enable DDM to abstract complex object shapes with significantly fewer primitives that offer broader geometry coverage and finer details. DDM is also capable of learning part-level semantic correspondences due to the differentiable and invertible properties of our primitive deformation. Moreover, DDM learning formulation is based on dynamic and kinematic modeling, which enables joint regularization of each sub-transformation during primitive fitting. Extensive experiments on \textit{ShapeNet} demonstrate that DDM outperforms the state-of-the-art in terms of reconstruction and part consistency by a notable margin.

Accurate 3D cardiac reconstruction from cine magnetic resonance imaging (cMRI) is crucial for improved cardiovascular disease diagnosis and understanding of the heart's motion. However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed cardiac volumes. To better reconstruct 3D cardiac volumes from sparse 2D image stacks, we propose a morphology-guided diffusion model for 3D cardiac volume reconstruction, DMCVR, that synthesizes high-resolution 2D images and corresponding 3D reconstructed volumes. Our method outperforms previous approaches by conditioning the cardiac morphology on the generative model, eliminating the time-consuming iterative optimization process of the latent code, and improving generation quality. The learned latent spaces provide global semantics, local cardiac morphology and details of each 2D cMRI slice with highly interpretable value to reconstruct 3D cardiac shape. Our experiments show that DMCVR is highly effective in several aspects, such as 2D generation and 3D reconstruction performance. With DMCVR, we can produce high-resolution 3D cardiac MRI reconstructions, surpassing current techniques. Our proposed framework has great potential for improving the accuracy of cardiac disease diagnosis and treatment planning. Code can be accessed at https://github.com/hexiaoxiao-cs/DMCVR., Comment: Accepted in MICCAI 2023

Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). However, teacher-student self-training, a powerful and widely used paradigm to leverage PLs, is rarely explored for OVD. This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs. To address these challenges, we propose SAS-Det that tames self-training for OVD from two key perspectives. First, we present a split-and-fusion (SAF) head that splits a standard detection into an open-branch and a closed-branch. This design can reduce noisy supervision from pseudo boxes. Moreover, the two branches learn complementary knowledge from different training data, significantly enhancing performance when fused together. Second, in our view, unlike in closed-set tasks, the PL distributions in OVD are solely determined by the teacher model. We introduce a periodic update strategy to decrease the number of updates to the teacher, thereby decreasing the frequency of changes in PL distributions, which stabilizes the training process. Extensive experiments demonstrate SAS-Det is both efficient and effective. SAS-Det outperforms recent models of the same scale by a clear margin and achieves 37.4 AP50 and 29.1 APr on novel categories of the COCO and LVIS benchmarks, respectively. Code is available at \url{https://github.com/xiaofeng94/SAS-Det}., Comment: Accepted to CVPR 2024. The supplementary document included

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case's CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score., Comment: 16 pages, 7 figures

Survival outcome assessment is challenging and inherently associated with multiple clinical factors (e.g., imaging and genomics biomarkers) in cancer. Enabling multimodal analytics promises to reveal novel predictive patterns of patient outcomes. In this study, we propose a multimodal transformer (PathOmics) integrating pathology and genomics insights into colon-related cancer survival prediction. We emphasize the unsupervised pretraining to capture the intrinsic interaction between tissue microenvironments in gigapixel whole slide images (WSIs) and a wide range of genomics data (e.g., mRNA-sequence, copy number variant, and methylation). After the multimodal knowledge aggregation in pretraining, our task-specific model finetuning could expand the scope of data utility applicable to both multi- and single-modal data (e.g., image- or genomics-only). We evaluate our approach on both TCGA colon and rectum cancer cohorts, showing that the proposed approach is competitive and outperforms state-of-the-art studies. Finally, our approach is desirable to utilize the limited number of finetuned samples towards data-efficient analytics for survival outcome prediction. The code is available at https://github.com/Cassie07/PathOmics., Comment: Accepted to MICCAI2023 (Top14%)

Recent text-to-image diffusion models have shown surprising performance in generating high-quality images. However, concerns have arisen regarding the unauthorized data usage during the training or fine-tuning process. One example is when a model trainer collects a set of images created by a particular artist and attempts to train a model capable of generating similar images without obtaining permission and giving credit to the artist. To address this issue, we propose a method for detecting such unauthorized data usage by planting the injected memorization into the text-to-image diffusion models trained on the protected dataset. Specifically, we modify the protected images by adding unique contents on these images using stealthy image warping functions that are nearly imperceptible to humans but can be captured and memorized by diffusion models. By analyzing whether the model has memorized the injected content (i.e., whether the generated images are processed by the injected post-processing function), we can detect models that had illegally utilized the unauthorized data. Experiments on Stable Diffusion and VQ Diffusion with different model training or fine-tuning methods (i.e, LoRA, DreamBooth, and standard training) demonstrate the effectiveness of our proposed method in detecting unauthorized data usages. Code: https://github.com/ZhentingWang/DIAGNOSIS., Comment: ICLR 2024

A major focus of clinical imaging workflow is disease diagnosis and management, leading to medical imaging datasets strongly tied to specific clinical objectives. This scenario has led to the prevailing practice of developing task-specific segmentation models, without gaining insights from widespread imaging cohorts. Inspired by the training program of medical radiology residents, we propose a shift towards universal medical image segmentation, a paradigm aiming to build medical image understanding foundation models by leveraging the diversity and commonality across clinical targets, body regions, and imaging modalities. Towards this goal, we develop Hermes, a novel context-prior learning approach to address the challenges of data heterogeneity and annotation differences in medical image segmentation. In a large collection of eleven diverse datasets (2,438 3D images) across five modalities (CT, PET, T1, T2 and cine MRI) and multiple body regions, we demonstrate the merit of the universal paradigm over the traditional paradigm on addressing multiple tasks within a single model. By exploiting the synergy across tasks, Hermes achieves state-of-the-art performance on all testing datasets and shows superior model scalability. Results on two additional datasets reveals Hermes' strong performance for transfer learning, incremental learning, and generalization to downstream tasks. Hermes's learned priors demonstrate an appealing trait to reflect the intricate relations among tasks and modalities, which aligns with the established anatomical and imaging principles in radiology. The code is available: https://github.com/yhygao/universal-medical-image-segmentation., Comment: Accepted by CVPR 2024

Tooth segmentation from intraoral scans is a crucial part of digital dentistry. Many Deep Learning based tooth segmentation algorithms have been developed for this task. In most of the cases, high accuracy has been achieved, although, most of the available tooth segmentation techniques make an implicit restrictive assumption of full jaw model and they report accuracy based on full jaw models. Medically, however, in certain cases, full jaw tooth scan is not required or may not be available. Given this practical issue, it is important to understand the robustness of currently available widely used Deep Learning based tooth segmentation techniques. For this purpose, we applied available segmentation techniques on partial intraoral scans and we discovered that the available deep Learning techniques under-perform drastically. The analysis and comparison presented in this work would help us in understanding the severity of the problem and allow us to develop robust tooth segmentation technique without strong assumption of full jaw model., Comment: accepted to IEEE EMBC 2023

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimodal representation. FDT is a set of learnable tokens representing certain visual-semantic concepts. Both images and texts are embedded using shared FDT by first grounding multimodal inputs to FDT space and then aggregating the activated FDT representations. The matched visual and semantic concepts are enforced to be represented by the same set of discrete tokens by a sparse activation constraint. As a result, the granularity gap between the two modalities is reduced. Through both quantitative and qualitative analyses, we demonstrate that using FDT representations in CLIP-style models improves cross-modal alignment and performance in visual recognition and vision-language downstream tasks. Furthermore, we show that our method can learn more comprehensive representations, and the learned FDT capture meaningful cross-modal correspondence, ranging from objects to actions and attributes., Comment: Accepted to CVPR 2023

Federated Learning has gained popularity among medical institutions since it enables collaborative training between clients (e.g., hospitals) without aggregating data. However, due to the high cost associated with creating annotations, especially for large 3D image datasets, clinical institutions do not have enough supervised data for training locally. Thus, the performance of the collaborative model is subpar under limited supervision. On the other hand, large institutions have the resources to compile data repositories with high-resolution images and labels. Therefore, individual clients can utilize the knowledge acquired in the public data repositories to mitigate the shortage of private annotated images. In this paper, we propose a federated few-shot learning method with dual knowledge distillation. This method allows joint training with limited annotations across clients without jeopardizing privacy. The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost. Extensive evaluations are conducted on 3D magnetic resonance knee images from a private clinical dataset. Our proposed method shows superior performance and less training time than other semi-supervised federated learning methods. Codes and additional visualization results are available at https://github.com/hexiaoxiao-cs/fedml-knee.

In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype interference persist. In this study, we introduce the Contrastive Prototypical Prompt (CPP) approach. Through task-specific prompt-tuning, underpinned by a contrastive learning objective, we effectively address both aforementioned challenges. Our evaluations on four challenging class-incremental benchmarks reveal that CPP achieves a significant 4% to 6% improvement over state-of-the-art methods. Importantly, CPP operates without a rehearsal buffer and narrows the performance divergence between continual and offline joint-learning, suggesting an innovative scheme for Transformer-based continual learning systems., Comment: Accept to WACV 2024. Code is available at https://github.com/LzVv123456/Contrastive-Prototypical-Prompt

Manual tooth segmentation of 3D tooth meshes is tedious and there is variations among dentists. %Manual tooth annotation of 3D tooth meshes is a tedious task. Several deep learning based methods have been proposed to perform automatic tooth mesh segmentation. Many of the proposed tooth mesh segmentation algorithms summarize the mesh cell as - the cell center or barycenter, the normal at barycenter, the cell vertices and the normals at the cell vertices. Summarizing of the mesh cell/triangle in this manner imposes an implicit structural constraint and makes it difficult to work with multiple resolutions which is done in many point cloud based deep learning algorithms. We propose a novel segmentation method which utilizes only the barycenter and the normal at the barycenter information of the mesh cell and yet achieves competitive performance. We are the first to demonstrate that it is possible to relax the implicit structural constraint and yet achieve superior segmentation performance, Comment: accepted at IEEE ISBI 2023 International Symposium on Biomedical Imaging

Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to disentangle domain-specific and domain-invariant features is key for achieving Domain Generalization (DG). However, existing DG methods can hardly achieve effective disentanglement to get high generalizability. To deal with this problem, we propose an efficient Contrastive Domain Disentanglement and Style Augmentation (CDDSA) framework for generalizable medical image segmentation. First, a disentangle network is proposed to decompose an image into a domain-invariant anatomical representation and a domain-specific style code, where the former is sent to a segmentation model that is not affected by the domain shift, and the disentangle network is regularized by a decoder that combines the anatomical and style codes to reconstruct the input image. Second, to achieve better disentanglement, a contrastive loss is proposed to encourage the style codes from the same domain and different domains to be compact and divergent, respectively. Thirdly, to further improve generalizability, we propose a style augmentation method based on the disentanglement representation to synthesize images in various unseen styles with shared anatomical structures. Our method was validated on a public multi-site fundus image dataset for optic cup and disc segmentation and an in-house multi-site Nasopharyngeal Carcinoma Magnetic Resonance Image (NPC-MRI) dataset for nasopharynx Gross Tumor Volume (GTVnx) segmentation. Experimental results showed that the proposed CDDSA achieved remarkable generalizability across different domains, and it outperformed several state-of-the-art methods in domain-generalizable segmentation., Comment: 14 pages, 8 figures

Models should be able to adapt to unseen data during test-time to avoid performance drops caused by inevitable distribution shifts in real-world deployment scenarios. In this work, we tackle the practical yet challenging test-time adaptation (TTA) problem, where a model adapts to the target domain without accessing the source data. We propose a simple recipe called \textit{Data-efficient Prompt Tuning} (DePT) with two key ingredients. First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation. We find such parameter-efficient finetuning can efficiently adapt the model representation to the target domain without overfitting to the noise in the learning objective. Second, DePT bootstraps the source representation to the target domain by memory bank-based online pseudo-labeling. A hierarchical self-supervised regularization specially designed for prompts is jointly optimized to alleviate error accumulation during self-training. With much fewer tunable parameters, DePT demonstrates not only state-of-the-art performance on major adaptation benchmarks VisDA-C, ImageNet-C, and DomainNet-126, but also superior data efficiency, i.e., adaptation with only 1\% or 10\% data without much performance degradation compared to 100\% data. In addition, DePT is also versatile to be extended to online or multi-source TTA settings.

Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at large scales is difficult. Recent studies focus on learning video-level temporal and discriminative information using contrastive learning, but overlook the hierarchical spatial-temporal nature of human skeletons. Different from such superficial supervision at the video level, we propose a self-supervised hierarchical pre-training scheme incorporated into a hierarchical Transformer-based skeleton sequence encoder (Hi-TRS), to explicitly capture spatial, short-term, and long-term temporal dependencies at frame, clip, and video levels, respectively. To evaluate the proposed self-supervised pre-training scheme with Hi-TRS, we conduct extensive experiments covering three skeleton-based downstream tasks including action recognition, action detection, and motion prediction. Under both supervised and semi-supervised evaluation protocols, our method achieves the state-of-the-art performance. Additionally, we demonstrate that the prior knowledge learned by our model in the pre-training stage has strong transfer capability for different downstream tasks., Comment: Accepted to ECCV 2022

Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However, it is still cumbersome to deploy the NAS techniques in real-world applications due to the fussy procedures and the supervised learning paradigm. In this work, we propose the self-supervised and weight-preserving neural architecture search (SSWP-NAS) as an extension of the current NAS framework by allowing the self-supervision and retaining the concomitant weights discovered during the search stage. As such, we simplify the workflow of NAS to a one-stage and proxy-free procedure. Experiments show that the architectures searched by the proposed framework achieve state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets without using manual labels. Moreover, we show that employing the concomitant weights as initialization consistently outperforms the random initialization and the two-stage weight pre-training method by a clear margin under semi-supervised learning scenarios. Codes are publicly available at https://github.com/LzVv123456/SSWP-NAS.

Transformers have demonstrated remarkable performance in natural language processing and computer vision. However, existing vision Transformers struggle to learn from limited medical data and are unable to generalize on diverse medical image tasks. To tackle these challenges, we present MedFormer, a data-scalable Transformer designed for generalizable 3D medical image segmentation. Our approach incorporates three key elements: a desirable inductive bias, hierarchical modeling with linear-complexity attention, and multi-scale feature fusion that integrates spatial and semantic information globally. MedFormer can learn across tiny- to large-scale data without pre-training. Comprehensive experiments demonstrate MedFormer's potential as a versatile segmentation backbone, outperforming CNNs and vision Transformers on seven public datasets covering multiple modalities (e.g., CT and MRI) and various medical targets (e.g., healthy organs, diseased tissues, and tumors). We provide public access to our models and evaluation pipeline, offering solid baselines and unbiased comparisons to advance a wide range of downstream clinical applications.

We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set. We learn a transferable reward signal formulated using the exemplary set by ordinal metric learning. Our proposed method enables test-time policy adaptation to new environments where the reward signals are not readily available, and outperforms fine-tuning approaches that are limited to annotated images. In addition, the transferable reward allows repurposing the trained agent from one specific class to another class. Experiments on corrupted MNIST, CU-Birds, and COCO datasets demonstrate the effectiveness of our approach., Comment: ICLR 2022

Magnetic Resonance (MR) image reconstruction from highly undersampled $k$-space data is critical in accelerated MR imaging (MRI) techniques. In recent years, deep learning-based methods have shown great potential in this task. This paper proposes a learned half-quadratic splitting algorithm for MR image reconstruction and implements the algorithm in an unrolled deep learning network architecture. We compare the performance of our proposed method on a public cardiac MR dataset against DC-CNN and LPDNet, and our method outperforms other methods in both quantitative results and qualitative results with fewer model parameters and faster reconstruction speed. Finally, we enlarge our model to achieve superior reconstruction quality, and the improvement is $1.76$ dB and $2.74$ dB over LPDNet in peak signal-to-noise ratio on $5\times$ and $10\times$ acceleration, respectively. Code for our method is publicly available at https://github.com/hellopipu/HQS-Net., Comment: accepted for MIDL2022

Whole abdominal organ segmentation is important in diagnosing abdomen lesions, radiotherapy, and follow-up. However, oncologists' delineating all abdominal organs from 3D volumes is time-consuming and very expensive. Deep learning-based medical image segmentation has shown the potential to reduce manual delineation efforts, but it still requires a large-scale fine annotated dataset for training, and there is a lack of large-scale datasets covering the whole abdomen region with accurate and detailed annotations for the whole abdominal organ segmentation. In this work, we establish a new large-scale \textit{W}hole abdominal \textit{OR}gan \textit{D}ataset (\textit{WORD}) for algorithm research and clinical application development. This dataset contains 150 abdominal CT volumes (30495 slices). Each volume has 16 organs with fine pixel-level annotations and scribble-based sparse annotations, which may be the largest dataset with whole abdominal organ annotation. Several state-of-the-art segmentation methods are evaluated on this dataset. And we also invited three experienced oncologists to revise the model predictions to measure the gap between the deep learning method and oncologists. Afterwards, we investigate the inference-efficient learning on the WORD, as the high-resolution image requires large GPU memory and a long inference time in the test stage. We further evaluate the scribble-based annotation-efficient learning on this dataset, as the pixel-wise manual annotation is time-consuming and expensive. The work provided a new benchmark for the abdominal multi-organ segmentation task, and these experiments can serve as the baseline for future research and clinical application development., Comment: Accepted to Medical Image Analysis, dataset at: https://github.com/HiLab-git/WORD (we corrected the results or description in this version.)

Automating sign language translation (SLT) is a challenging real world application. Despite its societal importance, though, research progress in the field remains rather poor. Crucially, existing methods that yield viable performance necessitate the availability of laborious to obtain gloss sequence groundtruth. In this paper, we attenuate this need, by introducing an end-to-end SLT model that does not entail explicit use of glosses; the model only needs text groundtruth. This is in stark contrast to existing end-to-end models that use gloss sequence groundtruth, either in the form of a modality that is recognized at an intermediate model stage, or in the form of a parallel output process, jointly trained with the SLT model. Our approach constitutes a Transformer network with a novel type of layers that combines: (i) local winner-takes-all (LWTA) layers with stochastic winner sampling, instead of conventional ReLU layers, (ii) stochastic weights with posterior distributions estimated via variational inference, and (iii) a weight compression technique at inference time that exploits estimated posterior variance to perform massive, almost lossless compression. We demonstrate that our approach can reach the currently best reported BLEU-4 score on the PHOENIX 2014T benchmark, but without making use of glosses for model training, and with a memory footprint reduced by more than 70%., Comment: In Proceedings of ICCV 2021

Weak supervision learning on classification labels has demonstrated high performance in various tasks, while a few pixel-level fine annotations are also affordable. Naturally a question comes to us that whether the combination of pixel-level (e.g., segmentation) and image level (e.g., classification) annotation can introduce further improvement. However in computational pathology this is a difficult task for this reason: High resolution of whole slide images makes it difficult to do end-to-end classification model training, which is challenging to research of weak or hybrid supervision learning in the past. To handle this problem, we propose a hybrid supervision learning framework for this kind of high resolution images with sufficient image-level coarse annotations and a few pixel-level fine labels. This framework, when applied in training patch model, can carefully make use of coarse image-level labels to refine generated pixel-level pseudo labels. Complete strategy is proposed to suppress pixel-level false positives and false negatives. A large hybrid annotated dataset is used to evaluate the effectiveness of hybrid supervision learning. By extracting pixel-level pseudo labels in initially image-level labeled samples, we achieve 5.2% higher specificity than purely training on existing labels while retaining 100% sensitivity, in the task of image-level classification to be positive or negative., Comment: Accepted in MICCAI2021

Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs). In this paper, we introduce two key ingredients to Transformer to address this challenge. First, in low-resolution stages of the generative process, standard global self-attention is replaced with the proposed multi-axis blocked self-attention which allows efficient mixing of local and global attention. Second, in high-resolution stages, we drop self-attention while only keeping multi-layer perceptrons reminiscent of the implicit neural function. To further improve the performance, we introduce an additional self-modulation component based on cross-attention. The resulting model, denoted as HiT, has a nearly linear computational complexity with respect to the image size and thus directly scales to synthesizing high definition images. We show in the experiments that the proposed HiT achieves state-of-the-art FID scores of 30.83 and 2.95 on unconditional ImageNet $128 \times 128$ and FFHQ $256 \times 256$, respectively, with a reasonable throughput. We believe the proposed HiT is an important milestone for generators in GANs which are completely free of convolutions. Our code is made publicly available at https://github.com/google-research/hit-gan, Comment: Accepted to NeurIPS 2021 (with updated ImageNet results). Code is available at https://github.com/google-research/hit-gan

Instance segmentation is of great importance for many biological applications, such as study of neural cell interactions, plant phenotyping, and quantitatively measuring how cells react to drug treatment. In this paper, we propose a novel box-based instance segmentation method. Box-based instance segmentation methods capture objects via bounding boxes and then perform individual segmentation within each bounding box region. However, existing methods can hardly differentiate the target from its neighboring objects within the same bounding box region due to their similar textures and low-contrast boundaries. To deal with this problem, in this paper, we propose an object-guided instance segmentation method. Our method first detects the center points of the objects, from which the bounding box parameters are then predicted. To perform segmentation, an object-guided coarse-to-fine segmentation branch is built along with the detection branch. The segmentation branch reuses the object features as guidance to separate target object from the neighboring ones within the same bounding box region. To further improve the segmentation quality, we design an auxiliary feature refinement module that densely samples and refines point-wise features in the boundary regions. Experimental results on three biological image datasets demonstrate the advantages of our method. The code will be available at https://github.com/yijingru/ObjGuided-Instance-Segmentation., Comment: Accepted in TMI

Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities. However, the cross-modal attention models of existing methods could be sub-optimal and inaccurate because there is no direct supervision provided during the training process. In this work, we propose two novel training strategies, namely Contrastive Content Re-sourcing (CCR) and Contrastive Content Swapping (CCS) constraints, to address such limitations. These constraints supervise the training of cross-modal attention models in a contrastive learning manner without requiring explicit attention annotations. They are plug-in training strategies and can be easily integrated into existing cross-modal attention models. Additionally, we introduce three metrics including Attention Precision, Recall, and F1-Score to quantitatively measure the quality of learned attention models. We evaluate the proposed constraints by incorporating them into four state-of-the-art cross-modal attention-based image-text matching models. Experimental results on both Flickr30k and MS-COCO datasets demonstrate that integrating these constraints improves the model performance in terms of both retrieval performance and attention metrics., Comment: Accepted to WACV 2023

Image and video synthesis are closely related areas aiming at generating content from noise. While rapid progress has been demonstrated in improving image-based models to handle large resolutions, high-quality renderings, and wide variations in image content, achieving comparable video generation results remains problematic. We present a framework that leverages contemporary image generators to render high-resolution videos. We frame the video synthesis problem as discovering a trajectory in the latent space of a pre-trained and fixed image generator. Not only does such a framework render high-resolution videos, but it also is an order of magnitude more computationally efficient. We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled. With such a representation, our framework allows for a broad range of applications, including content and motion manipulation. Furthermore, we introduce a new task, which we call cross-domain video synthesis, in which the image and motion generators are trained on disjoint datasets belonging to different domains. This allows for generating moving objects for which the desired video data is not available. Extensive experiments on various datasets demonstrate the advantages of our methods over existing video generation techniques. Code will be released at https://github.com/snap-research/MoCoGAN-HD., Comment: Accepted to ICLR 2021

Lung nodule detection from 3D Computed Tomography scans plays a vital role in efficient lung cancer screening. Despite the SOTA performance obtained by recent anchor-based detectors using CNNs for this task, they require predetermined anchor parameters such as the size, number, and aspect ratio of anchors, and have limited robustness when dealing with lung nodules with a massive variety of sizes. To overcome these problems, we propose a 3D sphere representation-based center-points matching detection network that is anchor-free and automatically predicts the position, radius, and offset of nodules without the manual design of nodule/anchor parameters. The SCPM-Net consists of two novel components: sphere representation and center points matching. First, to match the nodule annotation in clinical practice, we replace the commonly used bounding box with our proposed bounding sphere to represent nodules with the centroid, radius, and local offset in 3D space. A compatible sphere-based intersection over-union loss function is introduced to train the lung nodule detection network stably and efficiently. Second, we empower the network anchor-free by designing a positive center-points selection and matching process, which naturally discards pre-determined anchor boxes. An online hard example mining and re-focal loss subsequently enable the CPM process to be more robust, resulting in more accurate point assignment and mitigation of class imbalance. In addition, to better capture spatial information and 3D context for the detection, we propose to fuse multi-level spatial coordinate maps with the feature extractor and combine them with 3D squeeze-and-excitation attention modules. Experimental results on the LUNA16 dataset showed that our proposed framework achieves superior performance compared with existing anchor-based and anchor-free methods for lung nodule detection., Comment: accept to Medical Image Analysis

In the animation industry, cartoon videos are usually produced at low frame rate since hand drawing of such frames is costly and time-consuming. Therefore, it is desirable to develop computational models that can automatically interpolate the in-between animation frames. However, existing video interpolation methods fail to produce satisfying results on animation data. Compared to natural videos, animation videos possess two unique characteristics that make frame interpolation difficult: 1) cartoons comprise lines and smooth color pieces. The smooth areas lack textures and make it difficult to estimate accurate motions on animation videos. 2) cartoons express stories via exaggeration. Some of the motions are non-linear and extremely large. In this work, we formally define and study the animation video interpolation problem for the first time. To address the aforementioned challenges, we propose an effective framework, AnimeInterp, with two dedicated modules in a coarse-to-fine manner. Specifically, 1) Segment-Guided Matching resolves the "lack of textures" challenge by exploiting global matching among color pieces that are piece-wise coherent. 2) Recurrent Flow Refinement resolves the "non-linear and extremely large motion" challenge by recurrent predictions using a transformer-like architecture. To facilitate comprehensive training and evaluations, we build a large-scale animation triplet dataset, ATD-12K, which comprises 12,000 triplets with rich annotations. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art interpolation methods for animation videos. Notably, AnimeInterp shows favorable perceptual quality and robustness for animation scenarios in the wild. The proposed dataset and code are available at https://github.com/lisiyao21/AnimeInterp/., Comment: Accepted by CVPR21

Radiotherapy is a treatment where radiation is used to eliminate cancer cells. The delineation of organs-at-risk (OARs) is a vital step in radiotherapy treatment planning to avoid damage to healthy organs. For nasopharyngeal cancer, more than 20 OARs are needed to be precisely segmented in advance. The challenge of this task lies in complex anatomical structure, low-contrast organ contours, and the extremely imbalanced size between large and small organs. Common segmentation methods that treat them equally would generally lead to inaccurate small-organ labeling. We propose a novel two-stage deep neural network, FocusNetv2, to solve this challenging problem by automatically locating, ROI-pooling, and segmenting small organs with specifically designed small-organ localization and segmentation sub-networks while maintaining the accuracy of large organ segmentation. In addition to our original FocusNet, we employ a novel adversarial shape constraint on small organs to ensure the consistency between estimated small-organ shapes and organ shape prior knowledge. Our proposed framework is extensively tested on both self-collected dataset of 1,164 CT scans and the MICCAI Head and Neck Auto Segmentation Challenge 2015 dataset, which shows superior performance compared with state-of-the-art head and neck OAR segmentation methods., Comment: Accepted by Medical Image Analysis

Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf. In this work, we introduce a paradigm of designing recurrent deep networks whereby the output of the recurrent layer is derived from appropriate arguments from nonparametric statistics. A novel variational Bayesian sequence-to-sequence network architecture is proposed that consists of a) a full Gaussian posterior distribution for data-driven memory compression and b) a nonparametric Indian Buffet Process prior for regularization applied on the Gated Recurrent Unit non-gate weights. We dub our approach Stick-Breaking Recurrent network and show that it can achieve a substantial weight compression without diminishing modeling performance.

As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks. In the medical domain, however, large-scale and multi-parties data training and analyses are infeasible due to the privacy and data security concerns. In this paper, we propose an extendable and elastic learning framework to preserve privacy and security while enabling collaborative learning with efficient communication. The proposed framework is named distributed Asynchronized Discriminator Generative Adversarial Networks (AsynDGAN), which consists of a centralized generator and multiple distributed discriminators. The advantages of our proposed framework are five-fold: 1) the central generator could learn the real data distribution from multiple datasets implicitly without sharing the image data; 2) the framework is applicable for single-modality or multi-modality data; 3) the learned generator can be used to synthesize samples for down-stream learning tasks to achieve close-to-real performance as using actual samples collected from multiple data centers; 4) the synthetic samples can also be used to augment data or complete missing modalities for one single data center; 5) the learning process is more efficient and requires lower bandwidth than other distributed deep learning methods., Comment: arXiv admin note: text overlap with arXiv:2006.00080