{"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/gather-excite-exploiting-feature-context-in","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","arxiv_id":"1810.12348","date":"2018-10-29","proceeding":"NeurIPS 2018 12","authors":["Jie Hu","Li Shen","Samuel Albanie","Gang Sun","Andrea Vedaldi"],"abstract":"While the use of bottom-up local operators in convolutional neural networks\n(CNNs) matches well some of the statistics of natural images, it may also\nprevent such models from capturing contextual long-range feature interactions.\nIn this work, we propose a simple, lightweight approach for better context\nexploitation in CNNs. We do so by introducing a pair of operators: gather,\nwhich efficiently aggregates feature responses from a large spatial extent, and\nexcite, which redistributes the pooled information to local features. The\noperators are cheap, both in terms of number of added parameters and\ncomputational complexity, and can be integrated directly in existing\narchitectures to improve their performance. Experiments on several datasets\nshow that gather-excite can bring benefits comparable to increasing the depth\nof a CNN at a fraction of the cost. For example, we find ResNet-50 with\ngather-excite operators is able to outperform its 101-layer counterpart on\nImageNet with no additional learnable parameters. We also propose a parametric\ngather-excite operator pair which yields further performance gains, relate it\nto the recently-introduced Squeeze-and-Excitation Networks, and analyse the\neffects of these changes to the CNN feature activation statistics.","url_abs":"http://arxiv.org/abs/1810.12348v3","url_pdf":"http://arxiv.org/pdf/1810.12348v3.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":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/hujie-frank/GENet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/BayesWatch/pytorch-GENet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/Mind23-2/MindCode-48","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/Roypic/Attention_Code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/MindSpore-paper-code-3/code10/tree/main/GENet_Res50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/GENet_Res50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/cuihu1998/GENet-Res50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"gather-excite-exploiting-feature-context-in","repo_url":"https://github.com/mindspore-ai/models/blob/master/research/cv/GENet_Res50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[{"method_slug":"gather-excite-networks","method_name":"Gather-Excite Networks"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gather-excite-networks","name":"Gather-Excite Networks","full_name":"Gather-Excite Networks"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.12348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12348"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Roypic/Attention_Code","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/GENet_Res50","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/blob/master/research/cv/GENet_Res50","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cuihu1998/GENet-Res50","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BayesWatch/pytorch-GENet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-48","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hujie-frank/GENet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code10/tree/main/GENet_Res50","reach":null}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"Roypic/Attention_Code","repo_kind":"listed","path":"internal_attention_block/FcaNet/facnet.py","file_url":"https://github.com/Roypic/Attention_Code/blob/HEAD/internal_attention_block/FcaNet/facnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"4a4cb0de6e3e58c2","entry":"get_freq_indices","repo":"Roypic/Attention_Code","repo_kind":"listed","path":"internal_attention_block/FcaNet/layer.py","file_url":"https://github.com/Roypic/Attention_Code/blob/HEAD/internal_attention_block/FcaNet/layer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a4cb0de6e3e58c2"}},{"code_sha256_prefix":"7abfa32a2f1d7424","entry":"logsumexp_2d","repo":"Roypic/Attention_Code","repo_kind":"listed","path":"external_attention_block/CBAM.py","file_url":"https://github.com/Roypic/Attention_Code/blob/HEAD/external_attention_block/CBAM.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7abfa32a2f1d7424"}},{"code_sha256_prefix":"0cc65ffaab2532a3","entry":"fcanet34","repo":"Roypic/Attention_Code","repo_kind":"listed","path":"internal_attention_block/FcaNet/facnet.py","file_url":"https://github.com/Roypic/Attention_Code/blob/HEAD/internal_attention_block/FcaNet/facnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0cc65ffaab2532a3"}},{"code_sha256_prefix":"7fc89237b98c78bf","entry":"fcanet50","repo":"Roypic/Attention_Code","repo_kind":"listed","path":"internal_attention_block/FcaNet/facnet.py","file_url":"https://github.com/Roypic/Attention_Code/blob/HEAD/internal_attention_block/FcaNet/facnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7fc89237b98c78bf"}},{"code_sha256_prefix":"789378d75fb1946e","entry":"get_error","repo":"BayesWatch/pytorch-GENet","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/BayesWatch/pytorch-GENet/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"789378d75fb1946e"}},{"code_sha256_prefix":"35618d09788aec75","entry":"get_no_params","repo":"BayesWatch/pytorch-GENet","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/BayesWatch/pytorch-GENet/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35618d09788aec75"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}