Summary of Labellessface: Fair Metric Learning For Face Recognition Without Attribute Labels, by Tetsushi Ohki et al.
LabellessFace: Fair Metric Learning for Face Recognition without Attribute Labels
by Tetsushi Ohki, Yuya Sato, Masakatsu Nishigaki, Koichi Ito
First submitted to arxiv on: 14 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces a novel framework called “LabellessFace” to improve demographic bias in face recognition without requiring demographic group labeling. The framework proposes a new fairness enhancement metric, the class favoritism level, and an extension of existing margin-based metric learning, the fair class margin penalty. This method dynamically adjusts learning parameters based on class favoritism levels to promote fairness across all attributes. The authors demonstrate that this approach is effective for enhancing fairness while maintaining authentication accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make face recognition systems fairer by creating a new way to improve bias without needing labels for different groups of people. They introduce a special metric called the class favoritism level and use it to adjust how the system learns, so it doesn’t favor certain groups over others. This makes it more accurate and fair for everyone. |
Keywords
» Artificial intelligence » Face recognition
