Flow AM: Generating Point Cloud Global Explanations by Latent Alignment
This work addresses the trustworthiness issue in point cloud models for researchers and practitioners by providing a more plausible and faithful explanation method, though it is incremental as it builds on existing AM techniques.
The paper tackles the problem of generating trustworthy global explanations for point cloud models by proposing an activation flow-based Activation Maximization (AM) method that avoids generative models, and it shows that this approach dramatically enhances explanation perceptibility compared to other non-generative AM methods.
Although point cloud models have gained significant improvements in prediction accuracy over recent years, their trustworthiness is still not sufficiently investigated. In terms of global explainability, Activation Maximization (AM) techniques in the image domain are not directly transplantable due to the special structure of the point cloud models. Existing studies exploit generative models to yield global explanations that can be perceived by humans. However, the opacity of the generative models themselves and the introduction of additional priors call into question the plausibility and fidelity of the explanations. In this work, we demonstrate that when the classifier predicts different types of instances, the intermediate layer activations are differently activated, known as activation flows. Based on this property, we propose an activation flow-based AM method that generates global explanations that can be perceived without incorporating any generative model. Furthermore, we reveal that AM based on generative models fails the sanity checks and thus lack of fidelity. Extensive experiments show that our approach dramatically enhances the perceptibility of explanations compared to other AM methods that are not based on generative models. Our code is available at: https://github.com/Explain3D/FlowAM