{"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/semi-supervised-semantic-segmentation-via-2","title":"Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning","arxiv_id":"2110.05474","date":"2021-10-11","proceeding":"NeurIPS 2021 12","authors":["Hanzhe Hu","Fangyun Wei","Han Hu","Qiwei Ye","Jinshi Cui","LiWei Wang"],"abstract":"Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution. Existing approaches almost all neglect this problem, and treat categories equally. Some popular approaches such as consistency regularization or pseudo-labeling may even harm the learning of under-performing categories, that the predictions or pseudo labels of these categories could be too inaccurate to guide the learning on the unlabeled data. In this paper, we look into this problem, and propose a novel framework for semi-supervised semantic segmentation, named adaptive equalization learning (AEL). AEL adaptively balances the training of well and badly performed categories, with a confidence bank to dynamically track category-wise performance during training. The confidence bank is leveraged as an indicator to tilt training towards under-performing categories, instantiated in three strategies: 1) adaptive Copy-Paste and CutMix data augmentation approaches which give more chance for under-performing categories to be copied or cut; 2) an adaptive data sampling approach to encourage pixels from under-performing category to be sampled; 3) a simple yet effective re-weighting method to alleviate the training noise raised by pseudo-labeling. Experimentally, AEL outperforms the state-of-the-art methods by a large margin on the Cityscapes and Pascal VOC benchmarks under various data partition protocols. Code is available at https://github.com/hzhupku/SemiSeg-AEL","url_abs":"https://arxiv.org/abs/2110.05474v1","url_pdf":"https://arxiv.org/pdf/2110.05474v1.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":"semi-supervised-semantic-segmentation-via-2","repo_url":"https://github.com/hzhupku/semiseg-ael","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"copy-paste","method_name":"Copy-Paste"},{"method_slug":"cutmix","method_name":"CutMix"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-42","task":"Semi-Supervised Semantic Segmentation","dataset":"ADE20K 1/16 labeled","model":"AEL","rank_in_archive_order":3,"of":5,"metrics":{"Validation mIoU":"33.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-41","task":"Semi-Supervised Semantic Segmentation","dataset":"ADE20K 1/32 labeled","model":"AEL","rank_in_archive_order":3,"of":5,"metrics":{"Validation mIoU":"28.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":8,"of":33,"metrics":{"Validation mIoU":"77.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":10,"of":30,"metrics":{"Validation mIoU":"79.01%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":6,"of":23,"metrics":{"Validation mIoU":"80.28%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":10,"of":18,"metrics":{"Validation mIoU":"75.83%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-35","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 93 labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":1,"of":3,"metrics":{"Validation mIoU":"74.28"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":14,"of":27,"metrics":{"Validation mIoU":"78.06"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-36","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 331 labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":1,"of":1,"metrics":{"Validation mIoU":"76.97"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":4,"of":14,"metrics":{"Validation mIoU":"80.29%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-4","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 12.5% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":14,"of":38,"metrics":{"Validation mIoU":"77.57%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-21","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 6.25% labeled","model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":11,"of":19,"metrics":{"Validation mIoU":"77.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05474"}},"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":"deterministic:regex_extraction","url":"https://github.com/hzhupku/SemiSeg-AEL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hzhupku/semiseg-ael","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"df89ce7c7fa936b9","entry":"Criterion_cons","repo":"hzhupku/semiseg-ael","repo_kind":"official","path":"semseg/utils/loss_helper.py","file_url":"https://github.com/hzhupku/semiseg-ael/blob/HEAD/semseg/utils/loss_helper.py","link_basis":"first_harvest_node","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":"df89ce7c7fa936b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}