{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/residual-attention-network-for-image","title":"Residual Attention Network for Image Classification","arxiv_id":"1704.06904","date":"2017-04-23","proceeding":"CVPR 2017 7","authors":["Fei Wang","Mengqing Jiang","Chen Qian","Shuo Yang","Cheng Li","Honggang Zhang","Xiaogang Wang","Xiaoou Tang"],"abstract":"In this work, we propose \"Residual Attention Network\", a convolutional neural\nnetwork using attention mechanism which can incorporate with state-of-art feed\nforward network architecture in an end-to-end training fashion. Our Residual\nAttention Network is built by stacking Attention Modules which generate\nattention-aware features. The attention-aware features from different modules\nchange adaptively as layers going deeper. Inside each Attention Module,\nbottom-up top-down feedforward structure is used to unfold the feedforward and\nfeedback attention process into a single feedforward process. Importantly, we\npropose attention residual learning to train very deep Residual Attention\nNetworks which can be easily scaled up to hundreds of layers. Extensive\nanalyses are conducted on CIFAR-10 and CIFAR-100 datasets to verify the\neffectiveness of every module mentioned above. Our Residual Attention Network\nachieves state-of-the-art object recognition performance on three benchmark\ndatasets including CIFAR-10 (3.90% error), CIFAR-100 (20.45% error) and\nImageNet (4.8% single model and single crop, top-5 error). Note that, our\nmethod achieves 0.6% top-1 accuracy improvement with 46% trunk depth and 69%\nforward FLOPs comparing to ResNet-200. The experiment also demonstrates that\nour network is robust against noisy labels.","url_abs":"http://arxiv.org/abs/1704.06904v1","url_pdf":"http://arxiv.org/pdf/1704.06904v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/Celsuss/Residual_Attention_Network_for_Image_Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/Mungosin/Mozgalo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/PistonY/ResidualAttentionNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/Piyushdharkar/Residual-Attention-Aware-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/TooTouch/WhiteBox-Part1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/deontaepharr/Residual-Attention-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/marload/ConvNets-TensorFlow2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/phamquiluan/ResidualAttentionNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/pooruss/Residual-Attention-Network-Paddle2.1.2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/xiaoboCASIA/SV-X-Softmax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/2023-MindSpore-4/Code14/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/2023-MindSpore-4/Code6/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/AlKun25/ResCon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/code-implementation1/Code7/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/tengshaofeng/ResidualAttentionNetwork-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"residual-attention-network-for-image","repo_url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/ResidualAttentionNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"channel-spatial-attention","method_name":"Channel & Spatial attention"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[{"slug":"channel-spatial-attention","name":"Channel & Spatial attention","full_name":"Channel & Spatial attention"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Attention-92","rank_in_archive_order":696,"of":1060,"metrics":{"Top 1 Accuracy":"80.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.06904","atlas_url":"https://app.syntology.ai/?focus=1704.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.06904"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code6/tree/main/ResidualAttentionNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code5/tree/main/ResidualAttentionNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-216/tree/main/ResidualAttentionNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mungosin/Mozgalo","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PistonY/ResidualAttentionNetwork","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code7/tree/main/ResidualAttentionNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tengshaofeng/ResidualAttentionNetwork-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TooTouch/WhiteBox-Part1","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marload/ConvNets-TensorFlow2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AlKun25/ResCon","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/ResidualAttentionNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pooruss/Residual-Attention-Network-Paddle2.1.2","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiaoboCASIA/SV-X-Softmax","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deontaepharr/Residual-Attention-Network","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Piyushdharkar/Residual-Attention-Aware-Network","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/ResidualAttentionNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phamquiluan/ResidualAttentionNetwork","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Celsuss/Residual_Attention_Network_for_Image_Classification","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code14/tree/main/ResidualAttentionNet","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"1b6569cf9589515a","entry":"resetMetrics","repo":"Celsuss/Residual_Attention_Network_for_Image_Classification","repo_kind":"listed","path":"training.py","file_url":"https://github.com/Celsuss/Residual_Attention_Network_for_Image_Classification/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b6569cf9589515a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}