{"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/n-cps-generalising-cross-pseudo-supervision","title":"n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation","arxiv_id":"2112.07528","date":"2021-12-14","proceeding":null,"authors":["Dominik Filipiak","Piotr Tempczyk","Marek Cygan"],"abstract":"We present n-CPS - a generalisation of the recent state-of-the-art cross pseudo supervision (CPS) approach for the task of semi-supervised semantic segmentation. In n-CPS, there are n simultaneously trained subnetworks that learn from each other through one-hot encoding perturbation and consistency regularisation. We also show that ensembling techniques applied to subnetworks outputs can significantly improve the performance. To the best of our knowledge, n-CPS paired with CutMix outperforms CPS and sets the new state-of-the-art for Pascal VOC 2012 with (1/16, 1/8, 1/4, and 1/2 supervised regimes) and Cityscapes (1/16 supervised).","url_abs":"https://arxiv.org/abs/2112.07528v4","url_pdf":"https://arxiv.org/pdf/2112.07528v4.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":"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":"n-CPS (ResNet-50)","rank_in_archive_order":12,"of":33,"metrics":{"Validation mIoU":"77.61%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"n-CPS (ResNet-50)","rank_in_archive_order":14,"of":30,"metrics":{"Validation mIoU":"78.41%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"n-CPS (ResNet-50)","rank_in_archive_order":11,"of":23,"metrics":{"Validation mIoU":"79.29%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"n-CPS (ResNet-50)","rank_in_archive_order":9,"of":18,"metrics":{"Validation mIoU":"76.08"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"n-CPS (ResNet-101)","rank_in_archive_order":12,"of":27,"metrics":{"Validation mIoU":"78.97"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"n-CPS (ResNet-50)","rank_in_archive_order":21,"of":27,"metrics":{"Validation mIoU":"75.85"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"n-CPS (ResNet-101)","rank_in_archive_order":5,"of":14,"metrics":{"Validation mIoU":"80.26%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-15","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 50%","model":"n-CPS (ResNet-50)","rank_in_archive_order":10,"of":14,"metrics":{"Validation mIoU":"77.07%"},"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":"n-CPS (ResNet-101)","rank_in_archive_order":13,"of":38,"metrics":{"Validation mIoU":"77.99%"},"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":"n-CPS","rank_in_archive_order":22,"of":38,"metrics":{"Validation mIoU":"74.21%"},"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":"n-CPS (ResNet-101)","rank_in_archive_order":13,"of":19,"metrics":{"Validation mIoU":"75.86"},"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":"n-CPS (ResNet-50)","rank_in_archive_order":15,"of":19,"metrics":{"Validation mIoU":"72.03"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}