{"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/pixel-contrastive-consistent-semi-supervised","title":"Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation","arxiv_id":"2108.09025","date":"2021-08-20","proceeding":"ICCV 2021 10","authors":["Yuanyi Zhong","Bodi Yuan","Hong Wu","Zhiqiang Yuan","Jian Peng","Yu-Xiong Wang"],"abstract":"We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.","url_abs":"https://arxiv.org/abs/2108.09025v1","url_pdf":"https://arxiv.org/pdf/2108.09025v1.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":[],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-2","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/128 labeled","model":"PC2Seg","rank_in_archive_order":8,"of":9,"metrics":{"Validation mIoU":"40.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-1","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/256 labeled","model":"PC2Seg","rank_in_archive_order":8,"of":9,"metrics":{"Validation mIoU":"37.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-4","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/32 labeled","model":"PC2Seg","rank_in_archive_order":6,"of":7,"metrics":{"Validation mIoU":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/512 labeled","model":"PC2Seg","rank_in_archive_order":7,"of":8,"metrics":{"Validation mIoU":"29.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-3","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/64 labeled","model":"PC2Seg","rank_in_archive_order":8,"of":9,"metrics":{"Validation mIoU":"43.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.09025","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}