{"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/conformer-local-features-coupling-global","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","arxiv_id":"2105.03889","date":"2021-05-09","proceeding":"ICCV 2021 10","authors":["Zhiliang Peng","Wei Huang","Shanzhi Gu","Lingxi Xie","YaoWei Wang","Jianbin Jiao","Qixiang Ye"],"abstract":"Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take advantage of convolutional operations and self-attention mechanisms for enhanced representation learning. Conformer roots in the Feature Coupling Unit (FCU), which fuses local features and global representations under different resolutions in an interactive fashion. Conformer adopts a concurrent structure so that local features and global representations are retained to the maximum extent. Experiments show that Conformer, under the comparable parameter complexity, outperforms the visual transformer (DeiT-B) by 2.3% on ImageNet. On MSCOCO, it outperforms ResNet-101 by 3.7% and 3.6% mAPs for object detection and instance segmentation, respectively, demonstrating the great potential to be a general backbone network. Code is available at https://github.com/pengzhiliang/Conformer.","url_abs":"https://arxiv.org/abs/2105.03889v1","url_pdf":"https://arxiv.org/pdf/2105.03889v1.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":"conformer-local-features-coupling-global","repo_url":"https://github.com/pengzhiliang/Conformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-local-features-coupling-global","repo_url":"https://github.com/vasgaowei/TS-CAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-local-features-coupling-global","repo_url":"https://github.com/vasgaowei/ts-cam-voc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conformer-local-features-coupling-global","repo_url":"https://github.com/open-mmlab/mmclassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Conformer-B","rank_in_archive_order":359,"of":1060,"metrics":{"GFLOPs":"46.6","Number of params":"83.3M","Top 1 Accuracy":"84.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.03889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03889"}},"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/vasgaowei/TS-CAM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vasgaowei/ts-cam-voc","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/pengzhiliang/Conformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmclassification","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"unverified":5},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"samples":9,"ran":6,"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":"6dcea70dafba08f4","entry":"Attention","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6dcea70dafba08f4"}},{"code_sha256_prefix":"4f37b2a82fa6afcf","entry":"Block","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f37b2a82fa6afcf"}},{"code_sha256_prefix":"40b891c254ce0189","entry":"Block","repo":"pengzhiliang/Conformer","repo_kind":"official","path":"conformer.py","file_url":"https://github.com/pengzhiliang/Conformer/blob/HEAD/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40b891c254ce0189"}},{"code_sha256_prefix":"9a7e248223caba16","entry":"ConvBlock","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9a7e248223caba16"}},{"code_sha256_prefix":"96b1105f90d5364e","entry":"FCUDown","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96b1105f90d5364e"}},{"code_sha256_prefix":"8c8f0d76b23e394f","entry":"FCUUp","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c8f0d76b23e394f"}},{"code_sha256_prefix":"091a9a2477f8498d","entry":"Med_ConvBlock","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"091a9a2477f8498d"}},{"code_sha256_prefix":"60988e98d48434bd","entry":"Conformer","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"60988e98d48434bd"}},{"code_sha256_prefix":"9a8608e4e9d68c55","entry":"Conformer","repo":"vasgaowei/ts-cam-voc","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/ts-cam-voc/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","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":"9a8608e4e9d68c55"}},{"code_sha256_prefix":"1d063bc04388e460","entry":"Conformer","repo":"pengzhiliang/Conformer","repo_kind":"official","path":"conformer.py","file_url":"https://github.com/pengzhiliang/Conformer/blob/HEAD/conformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d063bc04388e460"}},{"code_sha256_prefix":"a957868ace3bde4d","entry":"ConvTransBlock","repo":"vasgaowei/TS-CAM","repo_kind":"listed","path":"lib/models/conformer.py","file_url":"https://github.com/vasgaowei/TS-CAM/blob/HEAD/lib/models/conformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a957868ace3bde4d"}},{"code_sha256_prefix":"0f5a4cd482b2ec56","entry":"ConvTransBlock","repo":"pengzhiliang/Conformer","repo_kind":"official","path":"conformer.py","file_url":"https://github.com/pengzhiliang/Conformer/blob/HEAD/conformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f5a4cd482b2ec56"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}