检索结果-内蒙古大学图书馆

Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Shu Luo, Luyang Wang, Qiong Chen, Hao Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen Futian China

Existing state-of-the-art methods for surgical phase recognition either rely on the extraction of spatial-temporal features at a short-range temporal resolution or adopt the sequential extraction of the spatial and temporal features across the entire temporal resolution. However, these methods have limitations in modeling spatial-temporal dependency and addressing spatial-temporal redundancy: 1) These methods fail to effectively model spatial-temporal dependency, due to the lack of long-range information or joint spatial-temporal modeling. 2) These methods utilize dense spatial features across the entire temporal resolution, resulting in significant spatial-temporal redundancy. In this paper, we propose the Surgical Transformer (Surgformer) to address the issues of spatial-temporal modeling and redundancy in an end-to-end manner, which employs divided spatial-temporal attention and takes a limited set of sparse frames as input. Moreover, we propose a novel Hierarchical Temporal Attention (HTA) to capture both global and local information within varied temporal resolutions from a target frame-centric perspective. Distinct from conventional temporal attention that primarily emphasizes dense long-range similarity, HTA not only captures long-term information but also considers local latent consistency among informative frames. HTA then employs pyramid feature aggregation to effectively utilize temporal information across diverse temporal resolutions, thereby enhancing the overall temporal representation. Extensive experiments on two challenging benchmark datasets verify that our proposed Surgformer performs favorably against the state-of-the-art methods. The code is released at https://***/isyangshu/Surgformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Transplantation (surgical)

Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Miao, Wenjun Pang, Guansong Li, Tianqi Bai, Xiao Zheng, Jin School of Computer Science and Engineering Beihang University China School of Computing and Information Systems Singapore Management University Singapore State Key Laboratory of Software Development Environment Jiangxi Research Institute Beihang University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these issues, current studies fit a prior distribution of auxiliary/pseudo OOD data to the long-tailed in-distribution (ID) data. However, it is difficult to obtain such an accurate prior distribution given the unknowingness of real OOD samples and heavy class imbalance in LTR. A straightforward solution to avoid the requirement of this prior is to learn an outlier class to encapsulate the OOD samples. The main challenge is then to tackle the aforementioned confusion between OOD samples and head/tail-class samples when learning the outlier class. To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence. Extensive empirical results on three popular benchmarks CIFAR10-LT, CIFAR100-LT, and ImageNet-LT demonstrate that COCL substantially outperforms state-of-the-art OOD detection methods in LTR while being able to improve the classification accuracy on ID data. Code is available at https://***/mala-lab/COCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

Dual Consistency Learning for Semi-Supervised Airway Segmentation

学校读者我要写书评

暂无评论

Dual Consistency Learning for Semi-Supervised Airway Segment...

Mechatronics, IoT and Industrial Informatics (ICMIII), International Conference on

作者： Mingshuang Li Yunyi Yuan Qiong Wang Yinling Qian Lei Zhu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Southern University of Science and Technology Shenzhen China Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9798350386639

ISBN: (纸本)9798350386646

Airway segmentation serves as an essential foundational process for both the diagnosis of lung conditions and the navigation of surgical interventions. Although numerous attempts have been proposed to address airway segmentation, the application of semi-supervised learning in this task has not yet been extensively investigated. In this study, we introduce an innovative semi-supervised learning framework that incorporates dual consistency learning during the re-training. Dual consistency learning exploits image-level and feature-level perturbations simultaneously to fully and efficiently extract additional information from unlabeled data. Specifically, image-level consistency learning employs a novel frequency domain data augmentation scheme to enforce topological feature capturing, and feature-level consistency learning could explore a broader perturbation space, thus realizing discriminative representation extraction from feature space. We carry out comprehensive experiments across various public datasets to substantiate the efficacy of our proposed methodology. The results illustrate that our framework attains remarkable performance levels, surpassing the current state-of-the-art approaches.

关键词： Measurement Image segmentation Mechatronics Navigation Perturbation methods Surgery Lung

HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation

学校读者我要写书评

暂无评论

HTML: Hybrid Temporal-scale Multimodal Learning Framework fo...

International Conference on computer Vision (ICCV)

作者： Mingfei Han Yali Wang Zhihui Li Lina Yao Xiaojun Chang Yu Qiao ReLER AAII UTS Data61 CSIRO Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shanghai AI Laboratory Shanghai China Shandong Artificial Intelligence Qilu University of Technology Department of Computer Vision Mohamed bin Zayed University of Artificial Intelligence

Referring Video Object Segmentation (RVOS) is to segment the object instance from a given video, according to the textual description of this object. However, in the open world, the object descriptions are often diversified in contents and flexible in lengths. This leads to the key difficulty in RVOS, i.e., various descriptions of different objects are corresponding to different temporal scales in the video, which is ignored by most existing approaches with single stride of frame sampling. To tackle this problem, we propose a concise Hybrid Temporal-scale Multimodal Learning (HTML) framework, which can effectively align lingual and visual features to discover core object semantics in the video, by learning multimodal interaction hierarchically from different temporal scales. More specifically, we introduce a novel inter-scale multimodal perception module, where the language queries dynamically interact with visual features across temporal scales. It can effectively reduce complex object confusion by passing video context among different scales. Finally, we conduct extensive experiments on the widely used benchmarks, including Ref-Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB-Sentences, where our HTML achieves state-of-the-art performance on all these datasets.

关键词：

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Network for LiDAR 3D Object Detection

学校读者我要写书评

暂无评论

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Net...

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Liu, Meng Niu, Jianwei Liu, Yu The China North Artificial Intelligence and Innovation Research Institute Beijing100072 China The China North Vehicle Research Institute Beijing100072 China The State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Hangzhou Innovation Institute Beihang University Hangzhou310051 China The Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou450001 China

ISBN: (纸本)9781665481090

Accurate and efficient 3D object detection in LiDAR point cloud is critical for autonomous driving. In this paper, we provide a solution for LiDAR-only detection which employs voxel features and a sparse convolution network. Specifically, we utilized voxel centers to encode point clouds' voxel features. Then, combining the sparse convolution method, we leveraged residual learning to design the backbone network. The detector output predicted results for multi-category and multi-object detection. Our method was evaluated on three popular and challenging datasets (KITTI, nuScence and Waymo). Experimental results demonstrated that the accuracy and speed (27.8 FPS) of our model could effectively support object detection for autonomous driving in various scenarios. © 2022 IEEE.

关键词： Object detection

Masked Image Training for Generalizable Deep Image Denoising

学校读者我要写书评

暂无评论

Masked Image Training for Generalizable Deep Image Denoising

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Haoyu Chen Jinjin Gu Yihao Liu Salma Abdel Magid Chao Dong Qiong Wang Hanspeter Pfister Lei Zhu The Hong Kong University of Science and Technology (Guangzhou) Shanghai AI Lab The University of Sydney ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Harvard University Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The Hong Kong University of Science and Technology

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of Transformer-based models that have achieved notable state-of-the-art results on various image tasks. However, deep learning-based methods often suffer from a lack of generalization ability. For example, deep models trained on Gaussian noise may perform poorly when tested on other noise distributions. To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training. Our method involves masking random pixels of the input image and reconstructing the missing information during training. We also mask out the features in the self-attention layers to avoid the impact of training-testing inconsistency. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios. Additionally, our interpretability analysis demonstrates the superiority of our method.

关键词：

Tackling Noisy Labels with Network Parameter Additive Decomposition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Jingyi Xia, Xiaobo Lan, Long Wu, Xinghao Yu, Jun Yang, Wenjing Han, Bo Liu, Tongliang The Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha410073 China The Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering University of Sydney DarlingtonNSW2008 Australia The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Department of Automation University of Science and Technology of China Hefei230026 China The Department of Computer Science Hong Kong Baptist University Hong Kong

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot distinguish the memorization of clean data and mislabeled data, resulting in the network still inevitably overfitting mislabeled data in the early training stage. In this paper, to decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, we perform additive decomposition on network parameters. Namely, all parameters are additively decomposed into two groups, i.e. , parameters w are decomposed as w = σ + γ. Afterward, the parameters σ are considered to memorize clean data, while the parameters γ are considered to memorize mislabeled data. Benefiting from the memorization effect, the updates of the parameters σ are encouraged to fully memorize clean data in early training, and then discouraged with the increase of training epochs to reduce interference of mislabeled data. The updates of the parameters γ are the opposite. In testing, only the parameters σ are employed to enhance generalization. Extensive experiments on both simulated and real-world benchmarks confirm the superior performance of our method. The implementation is available at: https://***/wangjingyi9924/TNLPAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing

学校读者我要写书评

暂无评论

Enabling Communication-Efficient Federated Learning via Dist...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yixuan Guan Xuefeng Liu Tao Ren Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Laboratory for Internet Software Technologies Institute of Software Chinese Academy of Sciences Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer from limited bandwidth and unreliable connections in uplink transmission. To address this problem, the gradient compression methods based on compressed sensing (CS) theory have been put forward recently. However, most existing CS-based works compress gradients independently, ignoring the gradient correlations between participants or adjacent communication rounds, which constrains the achievement of higher compression rates. In view of the above observation, we propose a novel gradient compression scheme named FedDCS, guided by distributed compressed sensing (DCS) theory. Following the design philosophy of separate encoding and joint decoding in DCS, FedDCS compresses gradients for participants in each round separately while reconstructing them at the central server jointly via fully exploiting correlated gradients from the previous round, which are known as side information (SI). Benefiting from this design, reconstruction performance is significantly improved with fewer decoding errors also iterations under the identical compression rate, and the total uploading bits to achieve model convergence are considerably reduced. Theoretical analysis and extensive experiments conducted on MNIST and Fashion-MNIST both verify the effectiveness of our approach.

关键词：

IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Jiancheng Zhou, Donghao Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Chinese University of Hong Kong Hong Kong

Single-shot face anti-spoofing (FAS) is a key technique for securing face recognition systems, and it requires only static images as input. However, single-shot FAS remains a challenging and under-explored problem due to two main reasons: 1) on the data side, learning FAS from RGB images is largely context-dependent, and single-shot images without additional annotations contain limited semantic information. 2) on the model side, existing single-shot FAS models are infeasible to provide proper evidence for their decisions, and FAS methods based on depth estimation require expensive per-pixel annotations. To address these issues, a large binocular NIR image dataset (BNI-FAS) is constructed and published, which contains more than 300,000 real face and plane attack images, and an Interpretable FAS Transformer (IFAST) is proposed that requires only weak supervision to produce interpretable predictions. Our IFAST can produce pixel-wise disparity maps by the proposed disparity estimation Transformer with Dynamic Matching Attention (DMA) block. Besides, a well-designed confidence map generator is adopted to cooperate with the proposed dual-teacher distillation module to obtain the final discriminant results. The comprehensive experiments show that our IFAST can achieve state-of-the-art results on BNI-FAS, proving the effectiveness of the single-shot FAS based on binocular NIR images. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation