{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/confidence-weighted-boundary-aware-learning","title":"Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation","arxiv_id":"2502.15152","date":"2025-02-21","proceeding":null,"authors":["Ebenezer Tarubinga","Jenifer Kalafatovich Espinoza"],"abstract":"Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilising unlabeled data alongside limited labeled samples. Existing SSSS methods often face challenges such as coupling, where over-reliance on initial labeled data leads to suboptimal learning; confirmation bias, where incorrect predictions reinforce themselves repeatedly; and boundary blur caused by insufficient boundary-awareness and ambiguous edge information. To address these issues, we propose CW-BASS, a novel framework for SSSS. In order to mitigate the impact of incorrect predictions, we assign confidence weights to pseudo-labels. Additionally, we leverage boundary-delineation techniques, which, despite being extensively explored in weakly-supervised semantic segmentation (WSSS) remain under-explored in SSSS. Specifically, our approach: (1) reduces coupling through a confidence-weighted loss function that adjusts the influence of pseudo-labels based on their predicted confidence scores, (2) mitigates confirmation bias with a dynamic thresholding mechanism that learns to filter out pseudo-labels based on model performance, (3) resolves boundary blur with a boundary-aware module that enhances segmentation accuracy near object boundaries, and (4) reduces label noise with a confidence decay strategy that progressively refines pseudo-labels during training. Extensive experiments on the Pascal VOC 2012 and Cityscapes demonstrate that our method achieves state-of-the-art performance. Moreover, using only 1/8 or 12.5\\% of labeled data, our method achieves a mIoU of 75.81 on Pascal VOC 2012, highlighting its effectiveness in limited-label settings.","url_abs":"https://arxiv.org/abs/2502.15152v1","url_pdf":"https://arxiv.org/pdf/2502.15152v1.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":"confidence-weighted-boundary-aware-learning","repo_url":"https://github.com/psychofict/CW-BASS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"pseudo-label-filtering","task_name":"Pseudo Label Filtering"},{"task_slug":"segmentation","task_name":"Segmentation"},{"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-3","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 100 samples labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":3,"of":13,"metrics":{"Validation mIoU":"65.87"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":13,"of":33,"metrics":{"Validation mIoU":"77.20%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":13,"of":30,"metrics":{"Validation mIoU":"78.43%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":12,"of":18,"metrics":{"Validation mIoU":"75.00"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-9","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 25% labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":20,"of":27,"metrics":{"Validation mIoU":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-27","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 92 labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":14,"of":17,"metrics":{"Validation mIoU":"72.8"},"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":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":18,"of":38,"metrics":{"Validation mIoU":"75.81%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-44","task":"Semi-Supervised Semantic Segmentation","dataset":"Pascal VOC 2012 50% labeled","model":"CW-BASS (DeepLab v3+ with ResNet-50)","rank_in_archive_order":3,"of":3,"metrics":{"Validation mIoU":"77.15"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"psychofict/CW-BASS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b3db76d372641e6135b50759a8d543c65c5a4ab8bdda4ec6bff30258c265395d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}