{"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-6","title":"Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization","arxiv_id":"2210.04388","date":"2022-10-10","proceeding":null,"authors":["Hai-Ming Xu","Lingqiao Liu","Qiuchen Bian","Zhen Yang"],"abstract":"Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation, i.e., regions belonging to the same class may exhibit a very different appearance even in the same picture. This diversity will make the label propagation hard from pixels to pixels. To address this problem, we propose a novel approach to regularize the distribution of within-class features to ease label propagation difficulty. Specifically, our approach encourages the consistency between the prediction from a linear predictor and the output from a prototype-based predictor, which implicitly encourages features from the same pseudo-class to be close to at least one within-class prototype while staying far from the other between-class prototypes. By further incorporating CutMix operations and a carefully-designed prototype maintenance strategy, we create a semi-supervised semantic segmentation algorithm that demonstrates superior performance over the state-of-the-art methods from extensive experimental evaluation on both Pascal VOC and Cityscapes benchmarks.","url_abs":"https://arxiv.org/abs/2210.04388v1","url_pdf":"https://arxiv.org/pdf/2210.04388v1.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-6","repo_url":"https://github.com/heimingx/semi_seg_proto","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"cutmix","method_name":"CutMix"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":17,"of":33,"metrics":{"Validation mIoU":"76.31%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":15,"of":30,"metrics":{"Validation mIoU":"78.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":15,"of":23,"metrics":{"Validation mIoU":"79.11%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":14,"of":18,"metrics":{"Validation mIoU":"73.41%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":7,"of":27,"metrics":{"Validation mIoU":"80.78"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":2,"of":14,"metrics":{"Validation mIoU":"80.91%"},"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":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":8,"of":38,"metrics":{"Validation mIoU":"80.71%"},"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":"PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","rank_in_archive_order":9,"of":19,"metrics":{"Validation mIoU":"78.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.04388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}