Verifying Deep Learning-based Decisions for Facial Expression Recognition
This addresses reliability issues in high-risk fields like clinical pain treatment, but it is incremental as it builds on existing explanation methods.
The paper tackled the problem of verifying deep learning decisions in facial expression recognition by proposing a three-step verification pipeline, which revealed that state-of-the-art neural networks may ignore relevant facial regions despite achieving high performance.
Neural networks with high performance can still be biased towards non-relevant features. However, reliability and robustness is especially important for high-risk fields such as clinical pain treatment. We therefore propose a verification pipeline, which consists of three steps. First, we classify facial expressions with a neural network. Next, we apply layer-wise relevance propagation to create pixel-based explanations. Finally, we quantify these visual explanations based on a bounding-box method with respect to facial regions. Although our results show that the neural network achieves state-of-the-art results, the evaluation of the visual explanations reveals that relevant facial regions may not be considered.