4.6 Article

Fair Facial Attribute Classification via Causal Graph-Based Attribute Translation

期刊

SENSORS
卷 22, 期 14, 页码 -

出版社

MDPI
DOI: 10.3390/s22145271

关键词

deep learning; fair classification; facial attribute classification

资金

  1. Institute of Information & communications Technology Planning & Evaluation (IITP) - Korea government(MSIT) [2022-0-00951, 2022-0-00184]

向作者/读者索取更多资源

Recent studies have shown concerns about racial and gender disparities in facial attribute classification. Simple disparate treatment is ineffective in reducing performance disparities due to the complex correlation between attributes and sensitive attributes. This paper proposes a method for achieving counterfactual fairness in facial attribute classification by generating synthetic images under factual and counterfactual assumptions. The method utilizes a causal graph-based attribute translation approach to generate realistic counterfactual images that consider the complex causal relationship among attributes.
Recent studies have raised concerns regarding racial and gender disparity in facial attribute classification performance. As these attributes are directly and indirectly correlated with the sensitive attribute in a complex manner, simple disparate treatment is ineffective in reducing performance disparity. This paper focuses on achieving counterfactual fairness for facial attribute classification. Each labeled input image is used to generate two synthetic replicas: one under factual assumptions about the sensitive attribute and one under counterfactual. The proposed causal graph-based attribute translation generates realistic counterfactual images that consider the complicated causal relationship among the attributes with an encoder-decoder framework. A causal graph represents complex relationships among the attributes and is used to sample factual and counterfactual facial attributes of the given face image. The encoder-decoder architecture translates the given facial image to have sampled factual or counterfactual attributes while preserving its identity. The attribute classifier is trained for fair prediction with counterfactual regularization between factual and corresponding counterfactual translated images. Extensive experimental results on the CelebA dataset demonstrate the effectiveness and interpretability of the proposed learning method for classifying multiple face attributes.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据