{"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/farcluss-fuzzy-adaptive-rebalancing-and","title":"FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation","arxiv_id":"2506.11142","date":"2025-06-11","proceeding":null,"authors":["Ebenezer Tarubinga","Jenifer Kalafatovich","Seong-Whan Lee"],"abstract":"Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction uncertainty. Current approaches often discard uncertain regions through strict thresholding favouring dominant classes. To address these limitations, we introduce a holistic framework that transforms uncertainty into a learning asset through four principal components: (1) fuzzy pseudo-labeling, which preserves soft class distributions from top-K predictions to enrich supervision; (2) uncertainty-aware dynamic weighting, that modulate pixel-wise contributions via entropy-based reliability scores; (3) adaptive class rebalancing, which dynamically adjust losses to counteract long-tailed class distributions; and (4) lightweight contrastive regularization, that encourage compact and discriminative feature embeddings. Extensive experiments on benchmarks demonstrate that our method outperforms current state-of-the-art approaches, achieving significant improvements in the segmentation of under-represented classes and ambiguous regions.","url_abs":"https://arxiv.org/abs/2506.11142v2","url_pdf":"https://arxiv.org/pdf/2506.11142v2.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":"farcluss-fuzzy-adaptive-rebalancing-and","repo_url":"https://github.com/psychofict/FARCLUSS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"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-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"FARCLUSS","rank_in_archive_order":5,"of":33,"metrics":{"Validation mIoU":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"FARCLUSS","rank_in_archive_order":4,"of":30,"metrics":{"Validation mIoU":"80.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"FARCLUSS","rank_in_archive_order":2,"of":23,"metrics":{"Validation mIoU":"81.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"FARCLUSS","rank_in_archive_order":5,"of":18,"metrics":{"Validation mIoU":"77.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"FARCLUSS","rank_in_archive_order":11,"of":27,"metrics":{"Validation mIoU":"79.0"},"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":"FARCLUSS","rank_in_archive_order":12,"of":38,"metrics":{"Validation mIoU":"78.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-44","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 50% labeled","model":"FARCLUSS","rank_in_archive_order":2,"of":3,"metrics":{"Validation mIoU":"80.3"},"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":"FARCLUSS","rank_in_archive_order":12,"of":19,"metrics":{"Validation mIoU":"76.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.11142","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}