A fine-grained approach for visual interpretability of convolutional neural networks

Alessia Amelio, Gianluca Bonifazi, Francesco Cauteruccio, Enrico Corradini, Michele Marchetti, Domenico Ursino, Luca Virgili

Abstract: Highlights•A framework for visual interpretability of CNNs through a multilayer network.•Approaches to compute heatmaps from multilayer networks.•Visual interpretability for VGG16 and Imagenet.•Computation of heatmaps with pixel-level rather than area-level precision.•Competitive performance of the proposed framework compared to existing ones.