Pyramid With Super Resolution for In-the-Wild Facial Expression Recognition
Facial Expression Recognition (FER) is a challenging task that improves natural human-computer interaction. This paper focuses on automatic FER on a single in-the-wild (ITW) image. ITW images suffer real problems of pose, direction, and input resolution. In this study, we propose a pyramid with super-resolution (PSR) network architecture to solve the ITW FER task. We also introduce a prior distribution label smoothing (PDLS) loss function that applies the additional prior knowledge of the confusion about each expression in the FER task. Experiments on the three most popular ITW FER datasets showed that our approach outperforms all the state-of-the-art methods.
PDF
AffectNet
RAF-DB
Results from the Paper
Ranked #10 on
Facial Expression Recognition (FER)
on RAF-DB
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Facial Expression Recognition (FER) | AffectNet | PSR (VGG-16) | Accuracy (7 emotion) | - | # 24 | ||
| Accuracy (8 emotion) | 60.68 | # 14 | |||||
| Facial Expression Recognition (FER) | RAF-DB | PSR | Overall Accuracy | 88.98 | # 10 |
