{"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-with","title":"Semi-Supervised Semantic Segmentation with High- and Low-level Consistency","arxiv_id":"1908.05724","date":"2019-08-15","proceeding":null,"authors":["Sudhanshu Mittal","Maxim Tatarchenko","Thomas Brox"],"abstract":"The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification with limited data has only drawn attention recently. In this work, we propose an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images. It uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The dual-branch approach reduces both the low-level and the high-level artifacts typical when training with few labels. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks - PASCAL VOC 2012, PASCAL-Context, and Cityscapes - the approach achieves new state-of-the-art in semi-supervised learning.","url_abs":"https://arxiv.org/abs/1908.05724v1","url_pdf":"https://arxiv.org/pdf/1908.05724v1.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-with","repo_url":"https://github.com/sud0301/semisup-semseg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"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":"s4GAN (DeepLab v2 ImageNet pre-trained)","rank_in_archive_order":32,"of":33,"metrics":{"Validation mIoU":"59.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-18","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 2% labeled","model":"S4GAN (DeepLabv2 with ResNet101, MSCOCO pre-trained)","rank_in_archive_order":3,"of":3,"metrics":{"Validation mIoU":"50.48%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"s4GAN (DeepLab v2 ImageNet pre-trained)","rank_in_archive_order":29,"of":30,"metrics":{"Validation mIoU":"61.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-19","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 5% labeled","model":"S4GAN (DeepLabv2 with ResNet101, MSCOCO pre-trained)","rank_in_archive_order":3,"of":3,"metrics":{"Validation mIoU":"55.61%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-11","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL Context 12.5% labeled","model":"s4GAN+MLMT (DeepLab v2 ImageNet pre-trained)","rank_in_archive_order":2,"of":2,"metrics":{"Validation mIoU":"35.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-12","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL Context 25% labeled","model":"s4GAN+MLMT (DeepLab v2 ImageNet pre-trained)","rank_in_archive_order":2,"of":2,"metrics":{"Validation mIoU":"37.8"},"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":"s4GAN + MLMT","rank_in_archive_order":29,"of":38,"metrics":{"Validation mIoU":"71.4%"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-4","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 12.5% labeled","model":"s4GAN+MLMT","rank_in_archive_order":33,"of":38,"metrics":{"Validation mIoU":"70.4%"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-4","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 12.5% labeled","model":"s4GAN+MLMT","rank_in_archive_order":35,"of":38,"metrics":{"Validation mIoU":"67.3%"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-6","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 2% labeled","model":"s4GAN + MLMT (DeepLab v2 MSCOCO/ImageNet pre-trained)","rank_in_archive_order":9,"of":12,"metrics":{"Validation mIoU":"63.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-6","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 2% labeled","model":"s4GAN+MLMT (DeepLab v3+ ImageNet pre-trained)","rank_in_archive_order":10,"of":12,"metrics":{"Validation mIoU":"62.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-6","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 2% labeled","model":"s4GAN+MLMT (DeepLab v2 ImageNet pre-trained)","rank_in_archive_order":11,"of":12,"metrics":{"Validation mIoU":"60.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-5","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 5% labeled","model":"s4GAN + MLMT (DeepLab v2 MSCOCO/ImageNet pre-trained)","rank_in_archive_order":10,"of":14,"metrics":{"Validation mIoU":"67.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-5","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 5% labeled","model":"s4GAN+MLMT (DeepLab v3+ ImageNet pre-trained)","rank_in_archive_order":11,"of":14,"metrics":{"Validation mIoU":"66.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-5","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 5% labeled","model":"s4GAN+MLMT (DeepLab v2 ImageNet pre-trained)","rank_in_archive_order":13,"of":14,"metrics":{"Validation mIoU":"62.9%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.05724","atlas_url":"https://app.syntology.ai/?focus=1908.05724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.05724"}},"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/sud0301/semisup-semseg","reach":null}],"summary":{"ran_honours":2,"ran_fixture":2},"by_repo_kind":{},"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":4,"samples":[{"code_sha256_prefix":"fcbd501f30a007d4","entry":"color_map","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fcbd501f30a007d4"}},{"code_sha256_prefix":"799a094d0124a46c","entry":"get_label_vector","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"799a094d0124a46c"}},{"code_sha256_prefix":"b3b7c1c716f4ca66","entry":"lr_poly","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b3b7c1c716f4ca66"}},{"code_sha256_prefix":"3d0fa6038b78822c","entry":"one_hot","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3d0fa6038b78822c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}