{"ID":2868447,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16704","arxiv_id":"2509.16704","title":"When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation","abstract":"While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence predictions as pseudo-labels. However, these methods cannot cope with network overconfidence tendency, where correct and incorrect predictions overlap significantly in high-confidence regions, making separation challenging and amplifying model cognitive bias. Meanwhile, the direct discarding of low-confidence predictions disrupts spatial-semantic continuity, causing critical context loss. We propose Confidence Separable Learning (CSL) to address these limitations. CSL formulates pseudo-label selection as a convex optimization problem within the confidence distribution feature space, establishing sample-specific decision boundaries to distinguish reliable from unreliable predictions. Additionally, CSL introduces random masking of reliable pixels to guide the network in learning contextual relationships from low-reliability regions, thereby mitigating the adverse effects of discarding uncertain predictions. Extensive experimental results on the Pascal, Cityscapes, and COCO benchmarks show that CSL performs favorably against state-of-the-art methods. Code and model weights are available at https://github.com/PanLiuCSU/CSL.","short_abstract":"While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence predictions as pseudo-labels. However, these methods cannot cope with network overconfi...","url_abs":"https://arxiv.org/abs/2509.16704","url_pdf":"https://arxiv.org/pdf/2509.16704v1","authors":"[\"Pan Liu\",\"Jinshi Liu\"]","published":"2025-09-20T14:23:09Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609591,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2868447,"paper_url":"https://arxiv.org/abs/2509.16704","paper_title":"When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation","repo_url":"https://github.com/PanLiuCSU/CSL","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}