# DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing

Source: [DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing](<https://www.sota2.com/research/paper/68fa7a531e209131cea8277e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:19.790Z

Authors: Xiaoqin Wang, Xianxu Hou, Meidan Ding, Junliang Chen, Kaijun Deng, Jinheng Xie, Linlin Shen

Published: 2025-08-02T08:02:06.000Z

## 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}}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.01250>)

[PDF](<https://arxiv.org/pdf/2508.01250.pdf>)
