Dahong Qian

Ruifei Zhang, Guanbin Li, Zhen Li et al.

Accurate polyp segmentation is of great significance for the diagnosis and treatment of colorectal cancer. However, it has always been very challenging due to the diverse shape and size of polyp. In recent years, state-of-the-art methods have achieved significant breakthroughs in this task with the help of deep convolutional neural networks. However, few algorithms explicitly consider the impact of the size and shape of the polyp and the complex spatial context on the segmentation performance, which results in the algorithms still being powerless for complex samples. In fact, segmentation of polyps of different sizes relies on different local and global contextual information for regional contrast reasoning. To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM). Specifically, LCA modules deliver local context features from encoder layers to decoder layers, enhancing the attention to the hard region which is determined by the prediction map of previous layer. GCM aims to further explore the global context features and send to the decoder layers. ASM is used for adaptive selection and aggregation of context features through channel-wise attention. Our proposed approach is evaluated on the EndoScene and Kvasir-SEG Datasets, and shows outstanding performance compared with other state-of-the-art methods. The code is available at https://github.com/ReaFly/ACSNet.

Suncheng Xiang, Jingsheng Gao, Mengyuan Guan et al.

Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. However, previous methods mainly focus on the visual representation learning, while neglect to explore the potential of semantic features during training, which easily leads to poor generalization capability when adapted to the new domain. In this paper, we propose a Multi-Modal Equivalent Transformer called MMET for more robust visual-semantic embedding learning on visual, textual and visual-textual tasks respectively. To further enhance the robust feature learning in the context of transformer, a dynamic masking mechanism called Masked Multimodal Modeling strategy (MMM) is introduced to mask both the image patches and the text tokens, which can jointly works on multimodal or unimodal data and significantly boost the performance of generalizable person Re-ID. Extensive experiments on benchmark datasets demonstrate the competitive performance of our method over previous approaches. We hope this method could advance the research towards visual-semantic representation learning. Our source code is also publicly available at https://github.com/JeremyXSC/MMET.

Suncheng Xiang, Hao Chen, Wei Ran et al.

Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. Recently, leveraging the supervised or semi-unsupervised learning paradigms, which benefits from the large-scale datasets and strong computing performance, has achieved a competitive performance on a specific target domain. However, when Re-ID models are directly deployed in a new domain without target samples, they always suffer from considerable performance degradation and poor domain generalization. To address this challenge, we propose a Deep Multimodal Fusion network to elaborate rich semantic knowledge for assisting in representation learning during the pre-training. Importantly, a multimodal fusion strategy is introduced to translate the features of different modalities into the common space, which can significantly boost generalization capability of Re-ID model. As for the fine-tuning stage, a realistic dataset is adopted to fine-tune the pre-trained model for better distribution alignment with real-world data. Comprehensive experiments on benchmarks demonstrate that our method can significantly outperform previous domain generalization or meta-learning methods with a clear margin. Our source code will also be publicly available at https://github.com/JeremyXSC/DMF.

Chengfeng Zhou, Songchang Chen, Chenming Xu et al.

Since data scarcity and data heterogeneity are prevailing for medical images, well-trained Convolutional Neural Networks (CNNs) using previous normalization methods may perform poorly when deployed to a new site. However, a reliable model for real-world clinical applications should be able to generalize well both on in-distribution (IND) and out-of-distribution (OOD) data (e.g., the new site data). In this study, we present a novel normalization technique called window normalization (WIN) to improve the model generalization on heterogeneous medical images, which is a simple yet effective alternative to existing normalization methods. Specifically, WIN perturbs the normalizing statistics with the local statistics computed on the window of features. This feature-level augmentation technique regularizes the models well and improves their OOD generalization significantly. Taking its advantage, we propose a novel self-distillation method called WIN-WIN for classification tasks. WIN-WIN is easily implemented with twice forward passes and a consistency constraint, which can be a simple extension for existing methods. Extensive experimental results on various tasks (6 tasks) and datasets (24 datasets) demonstrate the generality and effectiveness of our methods.

Yiming Bao, Xu Zhao, Dahong Qian

There exist challenging problems in 3D human pose estimation mission, such as poor performance caused by occlusion and self-occlusion. Recently, IMU-vision sensor fusion is regarded as valuable for solving these problems. However, previous researches on the fusion of IMU and vision data, which is heterogeneous, fail to adequately utilize either IMU raw data or reliable high-level vision features. To facilitate a more efficient sensor fusion, in this work we propose a framework called \emph{FusePose} under a parametric human kinematic model. Specifically, we aggregate different information of IMU or vision data and introduce three distinctive sensor fusion approaches: NaiveFuse, KineFuse and AdaDeepFuse. NaiveFuse servers as a basic approach that only fuses simplified IMU data and estimated 3D pose in euclidean space. While in kinematic space, KineFuse is able to integrate the calibrated and aligned IMU raw data with converted 3D pose parameters. AdaDeepFuse further develops this kinematical fusion process to an adaptive and end-to-end trainable manner. Comprehensive experiments with ablation studies demonstrate the rationality and superiority of the proposed framework. The performance of 3D human pose estimation is improved compared to the baseline result. On Total Capture dataset, KineFuse surpasses previous state-of-the-art which uses IMU only for testing by 8.6\%. AdaDeepFuse surpasses state-of-the-art which uses IMU for both training and testing by 8.5\%. Moreover, we validate the generalization capability of our framework through experiments on Human3.6M dataset.

Suncheng Xiang, Jiale Guan, Shilun Cai et al.

Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras, which plays an important role in the prevention and treatment of colorectal cancer in computer-aided diagnosis. However, traditional methods for object ReID directly adopting CNN models trained on the ImageNet dataset usually produce unsatisfactory retrieval performance on colonoscopic datasets due to the large domain gap. Worsely, these solutions typically learn unimodal modal representations on the basis of visual samples, which fails to explore complementary information from other different modalities. To address this challenge, we propose a novel Deep Multimodal Collaborative Learning framework named DMCL for polyp re-identification, which can effectively encourage multimodal knowledge collaboration and reinforce generalization capability in medical scenarios. On the basis of it, a dynamic multimodal feature fusion strategy is introduced to leverage the optimized visual-text representations for multimodal fusion via end-to-end training. Experiments on the standard benchmarks show the benefits of the multimodal setting over state-of-the-art unimodal ReID models, especially when combined with the collaborative multimodal fusion strategy. The code is publicly available at https://github.com/JeremyXSC/DMCL.

Qingzhong Chen, Shilun Cai, Crystal Cai et al.

Colonoscopic video retrieval, which is a critical part of polyp treatment, has great clinical significance for the prevention and treatment of colorectal cancer. However, retrieval models trained on action recognition datasets usually produce unsatisfactory retrieval results on colonoscopic datasets due to the large domain gap between them. To seek a solution to this problem, we construct a large-scale colonoscopic dataset named Colo-Pair for medical practice. Based on this dataset, a simple yet effective training method called Colo-SCRL is proposed for more robust representation learning. It aims to refine general knowledge from colonoscopies through masked autoencoder-based reconstruction and momentum contrast to improve retrieval performance. To the best of our knowledge, this is the first attempt to employ the contrastive learning paradigm for medical video retrieval. Empirical results show that our method significantly outperforms current state-of-the-art methods in the colonoscopic video retrieval task.

Hongwei Xu, Suncheng Xiang, Dahong Qian

The softmax-based loss functions and its variants (e.g., cosface, sphereface, and arcface) significantly improve the face recognition performance in wild unconstrained scenes. A common practice of these algorithms is to perform optimizations on the multiplication between the embedding features and the linear transformation matrix. However in most cases, the dimension of embedding features is given based on traditional design experience, and there is less-studied on improving performance using the feature itself when giving a fixed size. To address this challenge, this paper presents a softmax approximation method called SubFace, which employs the subspace feature to promote the performance of face recognition. Specifically, we dynamically select the non-overlapping subspace features in each batch during training, and then use the subspace features to approximate full-feature among softmax-based loss, so the discriminability of the deep model can be significantly enhanced for face recognition. Comprehensive experiments conducted on benchmark datasets demonstrate that our method can significantly improve the performance of vanilla CNN baseline, which strongly proves the effectiveness of subspace strategy with the margin-based loss.

Sijia Du, Chengfeng Zhou, Suncheng Xiang et al.

Objective: Depth estimation is crucial for endoscopic navigation and manipulation, but obtaining ground-truth depth maps in real clinical scenarios, such as the colon, is challenging. This study aims to develop a robust framework that generalizes well to real colonoscopy images, overcoming challenges like non-Lambertian surface reflection and diverse data distributions. Methods: We propose a framework combining a convolutional neural network (CNN) for capturing local features and a Transformer for capturing global information. An uncertainty-based fusion block was designed to enhance generalization by identifying complementary contributions from the CNN and Transformer branches. The network can be trained with simulated datasets and generalize directly to unseen clinical data without any fine-tuning. Results: Our method is validated on multiple datasets and demonstrates an excellent generalization ability across various datasets and anatomical structures. Furthermore, qualitative analysis in real clinical scenarios confirmed the robustness of the proposed method. Conclusion: The integration of local and global features through the CNN-Transformer architecture, along with the uncertainty-based fusion block, improves depth estimation performance and generalization in both simulated and real-world endoscopic environments. Significance: This study offers a novel approach to estimate depth maps for endoscopy images despite the complex conditions in clinic, serving as a foundation for endoscopic automatic navigation and other clinical tasks, such as polyp detection and segmentation.

Tianyu Zhou, Junyi Tang, Zehui Li et al.

Colonoscopic polyp diagnosis is pivotal for early colorectal cancer detection, yet traditional automated reporting suffers from inconsistencies and hallucinations due to the scarcity of high-quality multimodal medical data. To bridge this gap, we propose LDP, a novel framework leveraging multimodal large language models (MLLMs) for professional polyp diagnosis report generation. Specifically, we curate MMEndo, a multimodal endoscopic dataset comprising expert-annotated colonoscopy image-text pairs. We fine-tune the Qwen2-VL-7B backbone using Parameter-Efficient Fine-Tuning (LoRA) and align it with clinical standards via Direct Preference Optimization (DPO). Extensive experiments show that our LDP outperforms existing baselines on both automated metrics and rigorous clinical expert evaluations (achieving a Physician Score of 7.2/10), significantly reducing training computational costs by 833x compared to full fine-tuning. The proposed solution offers a scalable, clinically viable path for primary healthcare, with additional validation on the IU-XRay dataset confirming its robustness.

Yang Ding, Can Han, Sijia Du et al.

Real-time acquisition of accurate scene depth is essential for automated robotic minimally invasive surgery. Stereo matching with binocular endoscopy can provide this depth information. However, existing stereo matching methods, designed primarily for natural images, often struggle with endoscopic images due to fuzzy tissue boundaries and typically fail to meet real-time requirements for high-resolution endoscopic image inputs. To address these challenges, we propose \textbf{RRESM}, a real-time stereo matching method tailored for endoscopic images. Our approach integrates a 3D Mamba Coordinate Attention module that enhances cost aggregation through position-sensitive attention maps and long-range spatial dependency modeling via the Mamba block, generating a robust cost volume without substantial computational overhead. Additionally, we introduce a High-Frequency Disparity Optimization module that refines disparity predictions near tissue boundaries by amplifying high-frequency details in the wavelet domain. Evaluations on the SCARED and SERV-CT datasets demonstrate state-of-the-art matching accuracy with a real-time inference speed of 42 FPS. The code is available at https://github.com/Sonne-Ding/RRESM.

Yesheng Zhang, Xu Zhao, Dahong Qian

Camera calibration is a crucial technique which significantly influences the performance of many robotic systems. Robustness and high precision have always been the pursuit of diverse calibration methods. State-of-the-art calibration techniques based on classical Zhang's method, however, still suffer from environmental noise, radial lens distortion and sub-optimal parameter estimation. Therefore, in this paper, we propose a hybrid camera calibration framework which combines learning-based approaches with traditional methods to handle these bottlenecks. In particular, this framework leverages learning-based approaches to perform efficient distortion correction and robust chessboard corner coordinate encoding. For sub-pixel accuracy of corner detection, a specially-designed coordinate decoding algorithm with embed outlier rejection mechanism is proposed. To avoid sub-optimal estimation results, we improve the traditional parameter estimation by RANSAC algorithm and achieve stable results. Compared with two widely-used camera calibration toolboxes, experiment results on both real and synthetic datasets manifest the better robustness and higher precision of the proposed framework. The massive synthetic dataset is the basis of our framework's decent performance and will be publicly available along with the code at https://github.com/Easonyesheng/CCS.

Ruijia Chang, Suncheng Xiang, Chengyu Zhou et al.

Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods face significant challenges due to the inter-class similarity and intra-class variation of chromosomes. To address this issue, we propose a supervised contrastive learning strategy that is tailored to train model-agnostic deep networks for reliable chromosome classification. This method enables extracting fine-grained chromosomal embeddings in latent space. These embeddings effectively expand inter-class boundaries and reduce intra-class variations, enhancing their distinctiveness in predicting chromosome types. On top of two large-scale chromosome datasets, we comprehensively validate the power of our contrastive learning strategy in boosting cutting-edge deep networks such as Transformers and ResNets. Extensive results demonstrate that it can significantly improve models' generalization performance, with an accuracy improvement up to +4.5%. Codes and pretrained models will be released upon acceptance of this work.

Chen Liu, Can Han, Chengfeng Zhou et al.

Gesture recognition is a foundational task in human-machine interaction (HMI). While there has been significant progress in gesture recognition based on surface electromyography (sEMG), accurate recognition of predefined gestures only within a closed set is still inadequate in practice. It is essential to effectively discern and reject unknown gestures of disinterest in a robust system. Numerous methods based on prototype learning (PL) have been proposed to tackle this open set recognition (OSR) problem. However, they do not fully explore the inherent distinctions between known and unknown classes. In this paper, we propose a more effective PL method leveraging two novel and inherent distinctions, feature activation level and projection inconsistency. Specifically, the Feature Activation Enhancement Mechanism (FAEM) widens the gap in feature activation values between known and unknown classes. Furthermore, we introduce Orthogonal Prototype Learning (OPL) to construct multiple perspectives. OPL acts to project a sample from orthogonal directions to maximize the distinction between its two projections, where unknown samples will be projected near the clusters of different known classes while known samples still maintain intra-class similarity. Our proposed method simultaneously achieves accurate closed-set classification for predefined gestures and effective rejection for unknown gestures. Extensive experiments demonstrate its efficacy and superiority in open-set gesture recognition based on sEMG.

Yiming Bao, Xu Zhao, Dahong Qian

Temporal 3D human pose estimation from monocular videos is a challenging task in human-centered computer vision due to the depth ambiguity of 2D-to-3D lifting. To improve accuracy and address occlusion issues, inertial sensor has been introduced to provide complementary source of information. However, it remains challenging to integrate heterogeneous sensor data for producing physically rational 3D human poses. In this paper, we propose a novel framework, Real-time Optimization and Fusion (RTOF), to address this issue. We first incorporate sparse inertial orientations into a parametric human skeleton to refine 3D poses in kinematics. The poses are then optimized by energy functions built on both visual and inertial observations to reduce the temporal jitters. Our framework outputs smooth and biomechanically plausible human motion. Comprehensive experiments with ablation studies demonstrate its rationality and efficiency. On Total Capture dataset, the pose estimation error is significantly decreased compared to the baseline method.