DAM: Diffusion Activation Maximization for 3D Global Explanations
This work addresses the unreliability and opacity of point cloud models, which is a critical issue for domains like autonomous driving and healthcare, though it appears incremental as it builds on existing diffusion and explainability techniques.
The paper tackles the problem of explaining black-box point cloud models in safety-critical applications like autonomous driving and healthcare by proposing DAM, a diffusion-based method for generating 3D global explanations, which outperforms existing methods in perceptibility, representativeness, and diversity while significantly reducing generation time.
In recent years, the performance of point cloud models has been rapidly improved. However, due to the limited amount of relevant explainability studies, the unreliability and opacity of these black-box models may lead to potential risks in applications where human lives are at stake, e.g. autonomous driving or healthcare. This work proposes a DDPM-based point cloud global explainability method (DAM) that leverages Point Diffusion Transformer (PDT), a novel point-wise symmetric model, with dual-classifier guidance to generate high-quality global explanations. In addition, an adapted path gradient integration method for DAM is proposed, which not only provides a global overview of the saliency maps for point cloud categories, but also sheds light on how the attributions of the explanations vary during the generation process. Extensive experiments indicate that our method outperforms existing ones in terms of perceptibility, representativeness, and diversity, with a significant reduction in generation time. Our code is available at: https://github.com/Explain3D/DAM