{"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/learning-from-rich-semantics-and-coarse","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","arxiv_id":"2310.12152","date":"2023-10-18","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, yet it produces limited results due to (1) semantic ambiguity -- an image-level label only captures a salient part of the image, ignoring the remaining rich semantics within the image; and (2) location sensitivity -- the label highly depends on the locations and crops of the original image, which may change after data transformations like random cropping. To remedy this, we propose RichSem, a simple but effective method, which is robust to learn rich semantics from coarse locations without the need of accurate bounding boxes. RichSem leverages rich semantics from images, which are then served as additional soft supervision for training detectors. Specifically, we add a semantic branch to our detector to learn these soft semantics and enhance feature representations for long-tailed object detection. The semantic branch is only used for training and is removed during inference. RichSem achieves consistent improvements on both overall and rare-category of LVIS under different backbones and detectors. Our method achieves state-of-the-art performance without requiring complex training and testing procedures. Moreover, we show the effectiveness of our method on other long-tailed datasets with additional experiments. Code is available at \\url{https://github.com/MengLcool/RichSem}.","url_abs":"https://arxiv.org/abs/2310.12152v1","url_pdf":"https://arxiv.org/pdf/2310.12152v1.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":"learning-from-rich-semantics-and-coarse","repo_url":"https://github.com/MengLcool/RichSem","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"long-tailed-object-detection","task_name":"Long-tailed Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-lvis-v1-0-val","task":"Object Detection","dataset":"LVIS v1.0 val","model":"RichSem (Focal-H + ImageNet as weakly-supervised extra data)","rank_in_archive_order":5,"of":15,"metrics":{"box AP":"61.2","box APr":"61.2"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.12152","atlas_url":"https://app.syntology.ai/?focus=2310.12152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12152"}},"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/MengLcool/RichSem","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"29dbbaafa4be18e1","entry":"aligned_bilinear","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/cond_inst.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/cond_inst.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"29dbbaafa4be18e1"}},{"code_sha256_prefix":"ed1a308adb65f645","entry":"compute_locations","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/cond_inst.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/cond_inst.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed1a308adb65f645"}},{"code_sha256_prefix":"dc279ea790da466f","entry":"dn_post_process","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/dn_components.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/dn_components.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc279ea790da466f"}},{"code_sha256_prefix":"8ff1be65649a5265","entry":"get_fed_loss_inds","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/fed_loss.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/fed_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ff1be65649a5265"}},{"code_sha256_prefix":"1b256feaf07b9f3c","entry":"load_class_freq","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/fed_loss.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/fed_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b256feaf07b9f3c"}},{"code_sha256_prefix":"c7dccf840b25513b","entry":"create_timm_resnet_21k","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/backbone.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/backbone.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7dccf840b25513b"}},{"code_sha256_prefix":"a82091666b9db8cf","entry":"multi_head_attention_forward","repo":"MengLcool/RichSem","repo_kind":"official","path":"models/richsem/attention.py","file_url":"https://github.com/MengLcool/RichSem/blob/HEAD/models/richsem/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a82091666b9db8cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}