{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/perturbed-and-strict-mean-teachers-for-semi","title":"Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation","arxiv_id":"2111.12903","date":"2021-11-25","proceeding":"CVPR 2022 1","authors":["Yuyuan Liu","Yu Tian","Yuanhong Chen","Fengbei Liu","Vasileios Belagiannis","Gustavo Carneiro"],"abstract":"Consistency learning using input image, feature, or network perturbations has shown remarkable results in semi-supervised semantic segmentation, but this approach can be seriously affected by inaccurate predictions of unlabelled training images. There are two consequences of these inaccurate predictions: 1) the training based on the \"strict\" cross-entropy (CE) loss can easily overfit prediction mistakes, leading to confirmation bias; and 2) the perturbations applied to these inaccurate predictions will use potentially erroneous predictions as training signals, degrading consistency learning. In this paper, we address the prediction accuracy problem of consistency learning methods with novel extensions of the mean-teacher (MT) model, which include a new auxiliary teacher, and the replacement of MT's mean square error (MSE) by a stricter confidence-weighted cross-entropy (Conf-CE) loss. The accurate prediction by this model allows us to use a challenging combination of network, input data and feature perturbations to improve the consistency learning generalisation, where the feature perturbations consist of a new adversarial perturbation. Results on public benchmarks show that our approach achieves remarkable improvements over the previous SOTA methods in the field. Our code is available at https://github.com/yyliu01/PS-MT.","url_abs":"https://arxiv.org/abs/2111.12903v3","url_pdf":"https://arxiv.org/pdf/2111.12903v3.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":"perturbed-and-strict-mean-teachers-for-semi","repo_url":"https://github.com/yyliu01/ps-mt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet50, single scale inference)","rank_in_archive_order":14,"of":33,"metrics":{"Validation mIoU":"77.12%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference)","rank_in_archive_order":16,"of":30,"metrics":{"Validation mIoU":"78.38%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"PS-MT (DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference)","rank_in_archive_order":12,"of":23,"metrics":{"Validation mIoU":"79.22%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-10","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 1464 labels","model":"PS-MT\n(DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)","rank_in_archive_order":11,"of":17,"metrics":{"Validation mIoU":"80.01"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-10","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 1464 labels","model":"PS-MT\n(DeepLab v3+ with ImageNet-pretrained ResNet-50, single scale inference)","rank_in_archive_order":14,"of":17,"metrics":{"Validation mIoU":"78.08"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"PS-MT\n(DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)","rank_in_archive_order":13,"of":27,"metrics":{"Validation mIoU":"78.72"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"PS-MT\n(DeepLab v3+ with ImageNet-pretrained ResNet-101, single scale inference)","rank_in_archive_order":6,"of":14,"metrics":{"Validation mIoU":"79.76%"},"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":"PS-MT","rank_in_archive_order":11,"of":38,"metrics":{"Validation mIoU":"78.20%"},"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":"PS-MT","rank_in_archive_order":19,"of":38,"metrics":{"Validation mIoU":"75.70%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.12903","atlas_url":"https://app.syntology.ai/?focus=2111.12903","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2111.12903"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.12903\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.12903"},"call":"get_concepts_for_paper(arxiv_id=\"2111.12903\")"}],"by_repo":[{"repo":"yyliu01/ps-mt","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2106.14133","Liu_Perturbed_and_Strict_Mean_Teachers_for_Semi-Supervised_Semantic_Segmentation_CVPR_2022_paper"],"harvested_for_calls":[{"arxiv_id":"2106.14133","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.14133"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.14133\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"caadf7fd85c2ce8c9ee95c726e46c5229eaed5bfbedee14da59816fa73d68b2a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}