{"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/190411491","title":"Local Relation Networks for Image Recognition","arxiv_id":"1904.11491","date":"2019-04-25","proceeding":"ICCV 2019 10","authors":["Han Hu","Zheng Zhang","Zhenda Xie","Stephen Lin"],"abstract":"The convolution layer has been the dominant feature extractor in computer\nvision for years. However, the spatial aggregation in convolution is basically\na pattern matching process that applies fixed filters which are inefficient at\nmodeling visual elements with varying spatial distributions. This paper\npresents a new image feature extractor, called the local relation layer, that\nadaptively determines aggregation weights based on the compositional\nrelationship of local pixel pairs. With this relational approach, it can\ncomposite visual elements into higher-level entities in a more efficient manner\nthat benefits semantic inference. A network built with local relation layers,\ncalled the Local Relation Network (LR-Net), is found to provide greater\nmodeling capacity than its counterpart built with regular convolution on\nlarge-scale recognition tasks such as ImageNet classification.","url_abs":"http://arxiv.org/abs/1904.11491v1","url_pdf":"http://arxiv.org/pdf/1904.11491v1.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":"190411491","repo_url":"https://github.com/gan3sh500/local-relational-nets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190411491","repo_url":"https://github.com/microsoft/Swin-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190411491","repo_url":"https://github.com/MindCode-4/code-12/tree/main/local-relation-networks-for-image-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"190411491","repo_url":"https://github.com/MindCode-4/code-7/tree/main/local-relation-networks-for-image-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"190411491","repo_url":"https://github.com/MindSpore-scientific/code-6/tree/main/local-relation-networks-for-image-recognition","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":null,"task_name":"Relation"},{"task_slug":"relation-network","task_name":"Relation Network"}],"methods":[{"method_slug":"lrnet","method_name":"LRNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"lrnet","name":"LRNet","full_name":"Local Relation Network"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"LR-Net-26","rank_in_archive_order":939,"of":1060,"metrics":{"GFLOPs":"2.6","Number of params":"14.7M","Top 1 Accuracy":"75.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.11491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11491"}},"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/microsoft/Swin-Transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-12/tree/main/local-relation-networks-for-image-recognition","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-6/tree/main/local-relation-networks-for-image-recognition","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gan3sh500/local-relational-nets","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-7/tree/main/local-relation-networks-for-image-recognition","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":"591438f1e4ca7afb","entry":"combine_prior","repo":"gan3sh500/local-relational-nets","repo_kind":"listed","path":"layer.py","file_url":"https://github.com/gan3sh500/local-relational-nets/blob/HEAD/layer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"591438f1e4ca7afb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}