DisFaceRep: 弱监督人脸解析中共现面部组件的表示解缠
DisFaceRep: Representation Disentanglement for Co-occurring Facial Components in Weakly Supervised Face Parsing
AI总结：
针对弱监督人脸解析中面部组件高共现和相似导致的性能下降，提出DisFaceRep框架，通过显式共现解缠策略和文本引导解缠损失分离组件，在三个数据集上显著优于现有方法。
摘要：
人脸解析旨在将面部图像分割为关键组件，如眼睛、嘴唇和眉毛。现有方法依赖密集的像素级标注，但此类标注获取成本高昂且劳动密集。为降低标注成本，我们引入了弱监督人脸解析（WSFP），这是一种新的任务设置，仅使用弱监督（如图像级标签和自然语言描述）执行密集的面部组件分割。由于面部组件的高共现性和视觉相似性，WSFP带来了独特的挑战，导致激活模糊和解析性能下降。为解决此问题，我们提出了DisFaceRep，一种表示解缠框架，旨在通过显式和隐式机制分离共现的面部组件。具体而言，我们引入了一种共现组件解缠策略，以显式减少数据集级偏差，以及一种文本引导的组件解缠损失，以隐式利用语言监督指导组件分离。在CelebAMask-HQ、LaPa和Helen上的大量实验证明了WSFP的难度和DisFaceRep的有效性，其显著优于现有的弱监督语义分割方法。代码将在https://github.com/CVI-SZU/DisFaceRep发布。
英文摘要：
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}}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
