Toward Unbiased Facial Expression Recognition in the Wild via Cross-Dataset Adaptation

ByungOk Han, Woo-han Yun, Jang-Hee Yoo, Won Hwa KimIEEE Access 2020 · OpenReview

Abstract

Despite various success in computer vision with facial images (e.g., face detection, recognition, and generation), facial expression recognition is still a challenging problem yet to be solved. This is because of simple but fundamental bottlenecks: 1) no global agreement on different facial expressions, 2) significant dataset biases that prevent cross-dataset analysis for a large-scale study, and 3) high class imbalance in in-the-wild datasets that causes inconsistency in predicting expressions in images using a machine learning algorithm. To tackle these issues, we propose a novel Deep Learning approach via adaptive cross-dataset scheme. We combine multiple in-the-wild datasets to secure sufficient training samples while minimizing dataset bias using ideas of reversal gradients to retain generality. For this, we introduce a flexible objective function that can control for skewed label distributions in the dataset. Incorporating these ideas, together with the ResNet pipeline as a backbone, we carried extensive experiments to validate our ideas using three independent in-the-wild facial expression datasets, which first confirmed bias from different datasets and yielded improved performance on facial expression recognition using the multi-site dataset.
BibTeX
@inproceedings{han2020toward,
  author = {ByungOk Han and Woo-han Yun and Jang-Hee Yoo and Won Hwa Kim},
  title = {{Toward Unbiased Facial Expression Recognition in the Wild via Cross-Dataset Adaptation}},
  booktitle = {IEEE Access},
  year = {2020},
  url = {https://openreview.net/forum?id=CnnSI5p3tSW},
}

Loading related content...

Figure