Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations
This addresses the explainable AI problem for end-users by improving black-box model explanations, though it appears incremental as it builds on existing methods.
The paper tackles the problem of explaining deep neural network decisions by proposing IASSA, a framework that generates pixel importance maps using iterative adaptive sampling and spatial attention, achieving performance that matches or exceeds state-of-the-art methods on the MS-COCO dataset.
Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process to an end-user. In this paper, we address the explainable AI problem for deep neural networks with our proposed framework, named IASSA, which generates an importance map indicating how salient each pixel is for the model's prediction with an iterative and adaptive sampling module. We employ an affinity matrix calculated on multi-level deep learning features to explore long-range pixel-to-pixel correlation, which can shift the saliency values guided by our long-range and parameter-free spatial attention. Extensive experiments on the MS-COCO dataset show that our proposed approach matches or exceeds the performance of state-of-the-art black-box explanation methods.