Multi-model Ensemble Learning Method for Human Expression Recognition
This work addresses limitations in human-computer interaction systems by improving expression recognition for more diverse application scenarios, though it is incremental.
The paper tackled the problem of human expression recognition in real-life scenarios by proposing a multi-model ensemble learning method, achieving effective results on the AffWild2 dataset from the ABAW2022 Challenge.
Analysis of human affect plays a vital role in human-computer interaction (HCI) systems. Due to the difficulty in capturing large amounts of real-life data, most of the current methods have mainly focused on controlled environments, which limit their application scenarios. To tackle this problem, we propose our solution based on the ensemble learning method. Specifically, we formulate the problem as a classification task, and then train several expression classification models with different types of backbones--ResNet, EfficientNet and InceptionNet. After that, the outputs of several models are fused via model ensemble method to predict the final results. Moreover, we introduce the multi-fold ensemble method to train and ensemble several models with the same architecture but different data distributions to enhance the performance of our solution. We conduct many experiments on the AffWild2 dataset of the ABAW2022 Challenge, and the results demonstrate the effectiveness of our solution.