HSE-NN Team at the 4th ABAW Competition: Multi-task Emotion Recognition and Learning from Synthetic Images
This work addresses emotion recognition from static photos for affective behavior analysis, but it is incremental as it builds on existing models and competitions.
The HSE-NN team tackled multi-task emotion recognition and learning from synthetic images in the 4th ABAW competition, achieving a performance measure of 1.3 on the validation set, which is significantly higher than the baseline of 0.3, and an average validation F1 score 18% greater than the baseline.
In this paper, we present the results of the HSE-NN team in the 4th competition on Affective Behavior Analysis in-the-wild (ABAW). The novel multi-task EfficientNet model is trained for simultaneous recognition of facial expressions and prediction of valence and arousal on static photos. The resulting MT-EmotiEffNet extracts visual features that are fed into simple feed-forward neural networks in the multi-task learning challenge. We obtain performance measure 1.3 on the validation set, which is significantly greater when compared to either performance of baseline (0.3) or existing models that are trained only on the s-Aff-Wild2 database. In the learning from synthetic data challenge, the quality of the original synthetic training set is increased by using the super-resolution techniques, such as Real-ESRGAN. Next, the MT-EmotiEffNet is fine-tuned on the new training set. The final prediction is a simple blending ensemble of pre-trained and fine-tuned MT-EmotiEffNets. Our average validation F1 score is 18% greater than the baseline convolutional neural network.