Abstract | ||
---|---|---|
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators. These uncertainties lead to a key challenge of large-scale Facial Expression Recognition (FER) in deep learning era. To address this problem, this paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial images. Specifically, SCN suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over mini-batch to weight each training sample with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group. Experiments on synthetic FER datasets and our collected WebEmotion dataset validate the effectiveness of our method. Results on public benchmarks demonstrate that our SCN outperforms current state-of-the-art methods with 88.14% on RAF-DB, 60.23% on Affect-Net, and 89.35% on FERPlus. The code will be available at https://github.com/kaiwang960112/Self-Cure-Network. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CVPR42600.2020.00693 | 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
DocType | ISSN | Citations |
Conference | 1063-6919 | 2 |
PageRank | References | Authors |
0.36 | 33 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai Wang | 1 | 1734 | 195.03 |
Xiaojiang Peng | 2 | 395 | 21.83 |
Jianfei Yang | 3 | 221 | 23.81 |
Shijian Lu | 4 | 1346 | 93.57 |
Yu Qiao | 5 | 2267 | 152.01 |