{"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","title":"DMT: Dynamic Mutual Training for Semi-Supervised Learning","arxiv_id":"2004.08514","date":"2020-04-18","proceeding":null,"authors":["Zhengyang Feng","Qianyu Zhou","Qiqi Gu","Xin Tan","Guangliang Cheng","Xuequan Lu","Jianping Shi","Lizhuang Ma"],"abstract":"Recent semi-supervised learning methods use pseudo supervision as core idea, especially self-training methods that generate pseudo labels. However, pseudo labels are unreliable. Self-training methods usually rely on single model prediction confidence to filter low-confidence pseudo labels, thus remaining high-confidence errors and wasting many low-confidence correct labels. In this paper, we point out it is difficult for a model to counter its own errors. Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors. With this new viewpoint, we propose mutual training between two different models by a dynamically re-weighted loss function, called Dynamic Mutual Training (DMT). We quantify inter-model disagreement by comparing predictions from two different models to dynamically re-weight loss in training, where a larger disagreement indicates a possible error and corresponds to a lower loss value. Extensive experiments show that DMT achieves state-of-the-art performance in both image classification and semantic segmentation. Our codes are released at https://github.com/voldemortX/DST-CBC .","url_abs":"https://arxiv.org/abs/2004.08514v4","url_pdf":"https://arxiv.org/pdf/2004.08514v4.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","repo_url":"https://github.com/voldemortX/DST-CBC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"DMT (WRN-28-2)","rank_in_archive_order":27,"of":49,"metrics":{"Percentage error":"5.79"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-3","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 100 samples labeled","model":"DMT (DeepLab v2 MSCOCO/ImageNet pre-trained)","rank_in_archive_order":11,"of":13,"metrics":{"Validation mIoU":"54.80%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"DMT (DeepLab v2 MSCOCO/ImageNet pre-trained)","rank_in_archive_order":28,"of":33,"metrics":{"Validation mIoU":"63.03%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-10","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 1464 labels","model":"DMT (DeepLab v2, ResNet-50)","rank_in_archive_order":15,"of":17,"metrics":{"Validation mIoU":"74.85"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-7","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 1% labeled","model":"DMT (DeepLab v2 MSCOCO pre-trained)","rank_in_archive_order":3,"of":6,"metrics":{"Validation mIoU":"63.04%"},"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":"DMT","rank_in_archive_order":26,"of":38,"metrics":{"Validation mIoU":"72.70%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-6","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 2% labeled","model":"DMT (DeepLab v2 MSCOCO pre-trained)","rank_in_archive_order":4,"of":12,"metrics":{"Validation mIoU":"67.15%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-5","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 5% labeled","model":"DMT (DeepLab v2 MSCOCO/ImageNet pre-trained)","rank_in_archive_order":5,"of":14,"metrics":{"Validation mIoU":"69.92%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.08514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08514"}},"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/voldemortX/DST-CBC","reach":null}],"summary":{"ran_honours":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":"837df0414a9e9631","entry":"test","repo":"voldemortX/DST-CBC","repo_kind":"official","path":"classification/main_dmt.py","file_url":"https://github.com/voldemortX/DST-CBC/blob/HEAD/classification/main_dmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"837df0414a9e9631"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}