{"ID":2887547,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01250","arxiv_id":"2508.01250","title":"DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing","abstract":"Face parsing aims to segment facial images into key components such as eyes, lips, and eyebrows. While existing methods rely on dense pixel-level annotations, such annotations are expensive and labor-intensive to obtain. To reduce annotation cost, we introduce Weakly Supervised Face Parsing (WSFP), a new task setting that performs dense facial component segmentation using only weak supervision, such as image-level labels and natural language descriptions. WSFP introduces unique challenges due to the high co-occurrence and visual similarity of facial components, which lead to ambiguous activations and degraded parsing performance. To address this, we propose DisFaceRep, a representation disentanglement framework designed to separate co-occurring facial components through both explicit and implicit mechanisms. Specifically, we introduce a co-occurring component disentanglement strategy to explicitly reduce dataset-level bias, and a text-guided component disentanglement loss to guide component separation using language supervision implicitly. Extensive experiments on CelebAMask-HQ, LaPa, and Helen demonstrate the difficulty of WSFP and the effectiveness of DisFaceRep, which significantly outperforms existing weakly supervised semantic segmentation methods. The code will be released at \\href{https://github.com/CVI-SZU/DisFaceRep}{\\textcolor{cyan}{https://github.com/CVI-SZU/DisFaceRep}}.","short_abstract":"Face parsing aims to segment facial images into key components such as eyes, lips, and eyebrows. While existing methods rely on dense pixel-level annotations, such annotations are expensive and labor-intensive to obtain. To reduce annotation cost, we introduce Weakly Supervised Face Parsing (WSFP), a new task setting t...","url_abs":"https://arxiv.org/abs/2508.01250","url_pdf":"https://arxiv.org/pdf/2508.01250v1","authors":"[\"Xiaoqin Wang\",\"Xianxu Hou\",\"Meidan Ding\",\"Junliang Chen\",\"Kaijun Deng\",\"Jinheng Xie\",\"Linlin Shen\"]","published":"2025-08-02T08:02:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611447,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2887547,"paper_url":"https://arxiv.org/abs/2508.01250","paper_title":"DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing","repo_url":"https://github.com/CVI-SZU/DisFaceRep","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}