Towards Visually Explaining Video Understanding Networks with Perturbation
This addresses the need for explainable AI in video analysis, offering a method applicable to diverse network structures, though it is incremental as it builds on existing perturbation-based approaches for images.
The paper tackles the problem of explaining black-box video understanding networks by proposing a generic perturbation-based method that visualizes influential input regions, enhanced with a novel loss function for spatial and temporal smoothness, and experimental results verify its effectiveness.
''Making black box models explainable'' is a vital problem that accompanies the development of deep learning networks. For networks taking visual information as input, one basic but challenging explanation method is to identify and visualize the input pixels/regions that dominate the network's prediction. However, most existing works focus on explaining networks taking a single image as input and do not consider the temporal relationship that exists in videos. Providing an easy-to-use visual explanation method that is applicable to diversified structures of video understanding networks still remains an open challenge. In this paper, we investigate a generic perturbation-based method for visually explaining video understanding networks. Besides, we propose a novel loss function to enhance the method by constraining the smoothness of its results in both spatial and temporal dimensions. The method enables the comparison of explanation results between different network structures to become possible and can also avoid generating the pathological adversarial explanations for video inputs. Experimental comparison results verified the effectiveness of our method.