{"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/logic-induced-diagnostic-reasoning-for-semi","title":"Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation","arxiv_id":"2308.12595","date":"2023-08-24","proceeding":"ICCV 2023 1","authors":["Chen Liang","Wenguan Wang","Jiaxu Miao","Yi Yang"],"abstract":"Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.","url_abs":"https://arxiv.org/abs/2308.12595v1","url_pdf":"https://arxiv.org/pdf/2308.12595v1.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":"diagnostic","task_name":"Diagnostic"},{"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-coco-2","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/128 labeled","model":"LogicDiag","rank_in_archive_order":5,"of":9,"metrics":{"Validation mIoU":"45.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-1","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/256 labeled","model":"LogicDiag","rank_in_archive_order":5,"of":9,"metrics":{"Validation mIoU":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-4","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/32 labeled","model":"LogicDiag","rank_in_archive_order":4,"of":7,"metrics":{"Validation mIoU":"50.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/512 labeled","model":"LogicDiag","rank_in_archive_order":4,"of":8,"metrics":{"Validation mIoU":"33.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-3","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/64 labeled","model":"LogicDiag","rank_in_archive_order":4,"of":9,"metrics":{"Validation mIoU":"48.8"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-28","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 183 labeled","model":"LogicDiag (DeepLab v3+ with ResNet-101)","rank_in_archive_order":11,"of":16,"metrics":{"Validation mIoU":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-29","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 366 labeled","model":"LogicDiag (DeepLab v3+ with ResNet-101)","rank_in_archive_order":11,"of":15,"metrics":{"Validation mIoU":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-30","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 732 labeled","model":"LogicDiag (DeepLab v3+ with ResNet-101)","rank_in_archive_order":11,"of":16,"metrics":{"Validation mIoU":"79.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-27","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 92 labeled","model":"LogicDiag (DeepLab v3+ with ResNet-101)","rank_in_archive_order":13,"of":17,"metrics":{"Validation mIoU":"73.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.12595","atlas_url":"https://app.syntology.ai/?focus=2308.12595","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}