GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps
This addresses the need for better interpretability in computer vision models, though it appears incremental as it builds on existing explanation methods.
The paper tackles the problem of explaining predictions in visual similarity and classification models by introducing Gradient Activation Maps (GAM), which uses gradient and activation information from multiple layers to provide improved visual explanations, outperforming existing alternatives across various tasks and datasets.
We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activation information from multiple network layers, GAM offers improved visual explanations, when compared to existing alternatives. The algorithmic advantages of GAM are explained in detail, and validated empirically, where it is shown that GAM outperforms its alternatives across various tasks and datasets.