Enhancing Facial Data Diversity with Style-based Face Aging

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)(2020)

引用 10|浏览98
暂无评分
摘要
A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as gender, age, and race. If not mitigated, bias leads to algorithms that exhibit unfair behaviour towards such groups. In this work, we address the problem of increasing the diversity of face datasets with respect to age. Concretely, we propose a novel, generative style-based architecture for data augmentation that captures fine-grained aging patterns by conditioning on multi-resolution age-discriminative representations. By evaluating on several age-annotated datasets in both single- and cross-database experiments, we show that the proposed method outperforms state-of-the-art algorithms for age transfer, especially in the case of age groups that lie in the tails of the label distribution. We further show significantly increased diversity in the augmented datasets, outperforming all compared methods according to established metrics.
更多
查看译文
关键词
facial data diversity,style-based face aging,generative style-based architecture,data augmentation,multiresolution age-discriminative representations,age-annotated datasets,age transfer,age groups,training fair classifiers,fine-grained aging patterns
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要