{"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/learning-self-supervised-low-rank-network-for","title":"Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation","arxiv_id":"2203.10278","date":"2022-03-19","proceeding":null,"authors":["Junwen Pan","Pengfei Zhu","Kaihua Zhang","Bing Cao","Yu Wang","Dingwen Zhang","Junwei Han","QinGhua Hu"],"abstract":"Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS methods employ a sophisticated multi-stage training strategy to estimate pseudo-labels as precise as possible, but they suffer from high model complexity. In contrast, there exists another research line that trains a single network with image-level labels in one training cycle. However, such a single-stage strategy often performs poorly because of the compounding effect caused by inaccurate pseudo-label estimation. To address this issue, this paper presents a Self-supervised Low-Rank Network (SLRNet) for single-stage WSSS and SSSS. The SLRNet uses cross-view self-supervision, that is, it simultaneously predicts several complementary attentive LR representations from different views of an image to learn precise pseudo-labels. Specifically, we reformulate the LR representation learning as a collective matrix factorization problem and optimize it jointly with the network learning in an end-to-end manner. The resulting LR representation deprecates noisy information while capturing stable semantics across different views, making it robust to the input variations, thereby reducing overfitting to self-supervision errors. The SLRNet can provide a unified single-stage framework for various label-efficient semantic segmentation settings: 1) WSSS with image-level labeled data, 2) SSSS with a few pixel-level labeled data, and 3) SSSS with a few pixel-level labeled data and many image-level labeled data. Extensive experiments on the Pascal VOC 2012, COCO, and L2ID datasets demonstrate that our SLRNet outperforms both state-of-the-art WSSS and SSSS methods with a variety of different settings, proving its good generalizability and efficacy.","url_abs":"https://arxiv.org/abs/2203.10278v1","url_pdf":"https://arxiv.org/pdf/2203.10278v1.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":"learning-self-supervised-low-rank-network-for","repo_url":"https://github.com/DesertsP/SLRNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","task":"Weakly-Supervised Semantic Segmentation","dataset":"COCO 2014 val","model":"SLRNet","rank_in_archive_order":35,"of":39,"metrics":{"mIoU":"35.0"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"SLRNet","rank_in_archive_order":48,"of":60,"metrics":{"Mean IoU":"69.4"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"SLRNet(1-stage,ResNet38)","rank_in_archive_order":56,"of":60,"metrics":{"Mean IoU":"67.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"SLRNet","rank_in_archive_order":51,"of":73,"metrics":{"Mean IoU":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"SLRNet(1-stage)","rank_in_archive_order":62,"of":73,"metrics":{"Mean IoU":"67.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.10278","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}