Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition
This work addresses robustness issues in skeleton-based action recognition, an incremental analysis that could inform more robust learning methods for this domain.
The study used Fourier analysis to investigate the robustness of graph convolutional neural networks (GCNs) in skeleton-based action recognition, finding that adversarial training enhances robustness against adversarial attacks and common corruptions without a trade-off for low-frequency perturbations, as shown on the NTU RGB+D dataset.
Using Fourier analysis, we explore the robustness and vulnerability of graph convolutional neural networks (GCNs) for skeleton-based action recognition. We adopt a joint Fourier transform (JFT), a combination of the graph Fourier transform (GFT) and the discrete Fourier transform (DFT), to examine the robustness of adversarially-trained GCNs against adversarial attacks and common corruptions. Experimental results with the NTU RGB+D dataset reveal that adversarial training does not introduce a robustness trade-off between adversarial attacks and low-frequency perturbations, which typically occurs during image classification based on convolutional neural networks. This finding indicates that adversarial training is a practical approach to enhancing robustness against adversarial attacks and common corruptions in skeleton-based action recognition. Furthermore, we find that the Fourier approach cannot explain vulnerability against skeletal part occlusion corruption, which highlights its limitations. These findings extend our understanding of the robustness of GCNs, potentially guiding the development of more robust learning methods for skeleton-based action recognition.