检索结果-内蒙古大学图书馆

Learning to Predict Context-Adaptive Convolution for Semantic Segmentation 16th

学校读者我要写书评

暂无评论

Learning to Predict Context-Adaptive Convolution for Semanti...

16th European Conference on computer vision, ECCV 2020

作者： Liu, Jianbo He, Junjun Qiao, Yu Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory The Chinese University of Hong Kong Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SenseTime Research Hong Kong

ISBN: (纸本)9783030585945

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. © 2020, Springer Nature Switzerland AG.

关键词： Convolution

Dual-AI: Dual-path Actor Interaction Learning for Group Activity recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Mingfei Zhang, David Junhao Wang, Yali Yan, Rui Yao, Lina Chang, Xiaojun Qiao, Yu ReLER AAII UTS United States National University of Singapore Singapore ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China RMIT University Australia University of New South Wales Australia Shanghai AI Laboratory Shanghai China

Learning spatial-temporal relation among multiple actors is crucial for group activity recognition. Different group activities often show the diversified interactions between actors in the video. Hence, it is often difficult to model complex group activities from a single view of spatial-temporal actor evolution. To tackle this problem, we propose a distinct Dual-path Actor Interaction (Dual-AI) framework, which flexibly arranges spatial and temporal transformers in two complementary orders, enhancing actor relations by integrating merits from different spatiotemporal paths. Moreover, we introduce a novel Multi-scale Actor Contrastive Loss (MAC-Loss) between two interactive paths of Dual-AI. Via self-supervised actor consistency in both frame and video levels, MAC-Loss can effectively distinguish individual actor representations to reduce action confusion among different actors. Consequently, our Dual-AI can boost group activity recognition by fusing such discriminative features of different actors. To evaluate the proposed approach, we conduct extensive experiments on the widely used benchmarks, including Volleyball [24], Collective Activity [12], and NBA datasets [56]. The proposed Dual-AI achieves state-of-the-art performance on all these datasets. It is worth noting the proposed Dual-AI with 50% training data outperforms a number of recent approaches with 100% training data. This confirms the generalization power of Dual-AI for group activity recognition, even under the challenging scenarios of limited supervision. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Revisiting the Generalization Problem of Low-level vision Models Through the Lens of Image Deraining

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Jinfan You, Zhiyuan Gu, Jinjin Zhu, Kaiwen Xue, Tianfan Dong, Chao Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China The Chinese University of Hong Kong 999077 Hong Kong The University of Sydney NSW2006 Australia Shanghai Jiao Tong University Shanghai200240 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen University of Advanced Technology Shenzhen518055 China

Generalization remains a significant challenge for low-level vision models, which often struggle with unseen degradations in real-world scenarios despite their success in controlled benchmarks. In this paper, we revisit the generalization problem in low-level vision models. Image deraining is selected as a case study due to its well-defined and easily decoupled structure, allowing for more effective observation and analysis. Through comprehensive experiments, we reveal that the generalization issue is not primarily due to limited network capacity but rather the failure of existing training strategies, which lead networks to overfit specific degradation patterns. Our findings show that guiding networks to focus on learning the underlying image content, rather than the degradation patterns, is key to improving generalization. We demonstrate that balancing the complexity of background images and degradations in the training data helps networks better fit the image distribution. Furthermore, incorporating content priors from pre-trained generative models significantly enhances generalization. Experiments on both image deraining and image denoising validate the proposed strategies. We believe the insights and solutions will inspire further research and improve the generalization of low-level vision models. Copyright © 2025, The Authors. All rights reserved.

关键词： Image denoising

EfficientFCN: Holistically-Guided Decoding for Semantic Segmentation 1

学校读者我要写书评

暂无评论

16th European Conference on computer vision, ECCV 2020

作者： Liu, Jianbo He, Junjun Zhang, Jiawei Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory The Chinese University of Hong Kong Shatin Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SenseTime Research Beijing China

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. © 2020, Springer Nature Switzerland AG.

关键词： Semantic Segmentation

VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yi Zhang, Xuan Li, Ying Liang, Guixin Jiang, Yabing Qiu, Lixia Tang, Haiping Xie, Fei Yao, Wei Dai, Yi Qiao, Yu Wang, Yali ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shenzhen Bwell Technology Co. Ltd China Shenzhen Longhua Drainage Co. Ltd China Shanghai AI Laboratory Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Video understanding is an important problem in computer vision. Currently, the well-studied task in this research is human action recognition, where the clips are manually trimmed from the long videos, and a single class of human action is assumed for each clip. However, we may face more complicated scenarios in the industrial applications. For example, in the real-world urban pipe system, anomaly defects are fine-grained, multi-labeled, domain-relevant. To recognize them correctly, we need to understand the detailed video content. For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis. In particular, we introduce two high-quality video benchmarks, namely QV-Pipe and CCTV-Pipe, for anomaly inspection in the real-world urban pipe systems. Based on these new datasets, we will host two competitions including (1) Video Defect Classification on QV-Pipe and (2) Temporal Defect Localization on CCTV-Pipe. In this report, we describe the details of these benchmarks, the problem definitions of competition tracks, the evaluation metric, and the result summary. We expect that, this competition would bring new opportunities and challenges for video understanding in smart city and beyond. The details of our VideoPipe challenge can be found in https://***. Copyright © 2022, The Authors. All rights reserved.

关键词： Defects

Face-sketch learning with human sketch-drawing order enforcement

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第11期63卷 298-311页

作者： Liang CHANG Lihua JIN Lifen WENG Wentao CHAO Xuguang WANG Xiaoming DENG Qiulei DONG School of Artificial Intelligence Beijing Normal University Department of Design Art Xiamen University of Technology Department of Automation North China Electric Power University Beijing Key Laboratory of Human Computer Interactions Institute of Software Chinese Academy of Sciences National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences

Dear editor,Although face-sketch synthesis generates a sketch from a given face photo automatically [1], it is an open research problem in computer vision [2–4]. Recently, several deep neural network (DNN)methods for... 详细信息

关键词： face sketch synthesis deep neural network order enforcement image synthesis generative adversarial network

Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Ling Mao, Qirong Huang, Xiaohua Zhang, Feifei Zhang, Zhihong School of Computer Science and Communication Engineering Jiangsu University ZhenjiangJiangsu212013 China School of Computer Engineering Nanjing Institute of Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Xiamen University Xiamen China Center for Machine Vision and Signal Analysis University of Oulu Finland

Micro-Expression recognition has become challenging, as it is extremely difficult to extract the subtle facial changes of micro-expressions. Recently, several approaches proposed several expression-shared features algorithms for micro-expression recognition. However, they do not reveal the specific discriminative characteristics, which lead to sub-optimal performance. This paper proposes a novel Feature Refinement (FR) with expression-specific feature learning and fusion for micro-expression recognition. It aims to obtain salient and discriminative features for specific expressions and also predict expression by fusing the expression-specific features. FR consists of an expression proposal module with attention mechanism and a classification branch. First, an inception module is designed based on optical flow to obtain expression-shared features. Second, in order to extract salient and discriminative features for specific expression, expression-shared features are fed into an expression proposal module with attention factors and proposal loss. Last, in the classification branch, labels of categories are predicted by a fusion of the expression-specific features. Experiments on three publicly available databases validate the effectiveness of FR under different protocol. Results on public benchmarks demonstrate that our FR provides salient and discriminative information for micro-expression recognition. The results also show our FR achieves better or competitive performance with the existing state-of-the-art methods on micro-expression recognition. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

UniFormer: Unifying Convolution and Self-attention for Visual recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Kunchang Wang, Yali Zhang, Junhao Gao, Peng Song, Guanglu Liu, Yu Li, Hongsheng Qiao, Yu 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 Beijing100049 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China National University of Singapore Singapore Shanghai Artificial Intelligence Laboratory China SenseTime Research China The Chinese University of Hong Kong Hong Kong

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing tackling both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1K classification task. With only ImageNet-1K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks. It obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Moreover, we build an efficient UniFormer with a concise hourglass design of token shrinking and recovering, which achieves 2-4× higher throughput than the recent lightweight models. Code is av

关键词： Convolution

Detach and Enhance: Learning Disentangled Cross-modal Latent Representation for Efficient Face-Voice Association and Matching

学校读者我要写书评

暂无评论

Detach and Enhance: Learning Disentangled Cross-modal Latent...

IEEE International Conference on Data Mining (ICDM)

作者： Zhenning Yu Xin Liu Yiu-Ming Cheung Minghang Zhu Xing Xu Nannan Wang Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Dept. of Comput. Sci. and Institute of Research and Continuing Education HK Baptist University Hong Kong SAR China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Dept. of Computer Sci. and Eng. University of Electronic Science and Technology of China Chengdu China State Key Lab. of Integrated Services Networks & School of Telecommun. Eng. Xidian University Xi’an China

Many researches in cognitive science have shown that humans often perform face-voice association for various perception tasks, and some recent data mining works have been designed in emulating such ability intelligently. Nevertheless, most methods often suffer from the degraded performance when there exist semantically irrelevant interference factors across different modalities. To alleviate this concern, this paper presents an efficient Disentangled Cross-modal Latent Representation (DCLR) method to adaptively detach the discriminative feature attributes and enhance the face-voice association. To be specific, the proposed DCLR framework consists of two-stage cross-modal disentangling process. First, the former stage employs the supervised contrastive learning to push the representations of face-voice data from the same person closer while pulling those representations of different person away. Then, the latter stage freezes all the parameters of the former stage, and further innovates a multi-layer orthogonal decoupling scheme to learn the disentangled latent representations, while filtering out the modality-dependent irrelevant factors. Besides, the cross-modal reconstruction loss is further utilized to narrow down the semantic gap between heterogeneous feature expressions. Through the joint exploitation of the above, the proposed framework can well associate the face-voice data to benefit various kinds of cross-modal perception tasks. Extensive experiments verify the superiorities of the proposed face-voice association framework and show its competitive performances.

关键词： Representation learning Filtering Semantics Interference Data models Cognitive science Data mining