{"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/distribution-alignment-a-unified-framework","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","arxiv_id":"2103.16370","date":"2021-03-30","proceeding":"CVPR 2021 1","authors":["Songyang Zhang","Zeming Li","Shipeng Yan","Xuming He","Jian Sun"],"abstract":"Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the two-stage learning framework via ablative study. Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. Specifically, we develop an adaptive calibration function that enables us to adjust the classification scores for each data point. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks. We validate our method by extensive experiments on four tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework. The code and models will be made publicly available at: https://github.com/Megvii-BaseDetection/DisAlign","url_abs":"https://arxiv.org/abs/2103.16370v1","url_pdf":"https://arxiv.org/pdf/2103.16370v1.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":"distribution-alignment-a-unified-framework","repo_url":"https://github.com/Megvii-BaseDetection/DisAlign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"long-tail-learning","task_name":"Long-tail Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","task":"Long-tail Learning","dataset":"ImageNet-LT","model":"DisAlign","rank_in_archive_order":43,"of":69,"metrics":{"Top-1 Accuracy":"53.4"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-places-lt","task":"Long-tail Learning","dataset":"Places-LT","model":"DisAlign","rank_in_archive_order":20,"of":29,"metrics":{"Top-1 Accuracy":"39.3"},"uses_additional_data":false},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset":"iNaturalist 2018","model":"DisAlign","rank_in_archive_order":30,"of":43,"metrics":{"Top-1 Accuracy":"70.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.16370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.16370"}},"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/Megvii-BaseDetection/DisAlign","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"430a3a654e81b1db","entry":"build_roi_heads","repo":"Megvii-BaseDetection/DisAlign","repo_kind":"official","path":"instance_seg/lvis0.5/mask_rcnn/res50/mask_rcnn.res50.fpn.lvis.multiscale.cos_norm.disalign.1x/net.py","file_url":"https://github.com/Megvii-BaseDetection/DisAlign/blob/HEAD/instance_seg/lvis0.5/mask_rcnn/res50/mask_rcnn.res50.fpn.lvis.multiscale.cos_norm.disalign.1x/net.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":false,"mcp_get_code":{"code_sha256":"430a3a654e81b1db"}},{"code_sha256_prefix":"135c61a560b31bce","entry":"check_checkpoint","repo":"Megvii-BaseDetection/DisAlign","repo_kind":"official","path":"instance_seg/lvis0.5/mask_rcnn/res50/mask_rcnn.res50.fpn.lvis.multiscale.cos_norm.disalign.1x/config.py","file_url":"https://github.com/Megvii-BaseDetection/DisAlign/blob/HEAD/instance_seg/lvis0.5/mask_rcnn/res50/mask_rcnn.res50.fpn.lvis.multiscale.cos_norm.disalign.1x/config.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":false,"mcp_get_code":{"code_sha256":"135c61a560b31bce"}},{"code_sha256_prefix":"5e8f4e5f8be47375","entry":"get_class_grw_weight","repo":"Megvii-BaseDetection/DisAlign","repo_kind":"official","path":"semantic_seg/disalign/models/losses/grw_cross_entropy_loss.py","file_url":"https://github.com/Megvii-BaseDetection/DisAlign/blob/HEAD/semantic_seg/disalign/models/losses/grw_cross_entropy_loss.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":false,"mcp_get_code":{"code_sha256":"5e8f4e5f8be47375"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}