Poly-CAM: High resolution class activation map for convolutional neural networks

Alexandre Englebert, Olivier Cornu, Christophe De Vleeschouwer

Keywords: XAI, explainability, saliency map, CAM, deep learning, CNN, convolutional neural network

Abstract: The need for Explainable AI is increasing with the development of deep learning. The saliency maps derived from convolutional neural networks generally fail in localizing with accuracy the image features justifying the network prediction. This is because those maps are either low-resolution as for CAM (Zhou et al.,2016), or smooth as for perturbation-based methods (Zeiler & Fergus, 2014), or do correspond to a large number of widespread peaky spots as for gradient-based approaches (Sundararajan et al., 2017; Smilkov et al., 2017). In contrast, our work proposes to combine the information from earlier network layers with the one from later layers to produce a high resolution Class Activation Map that is competitive with the previous art in term of insertion-deletion faithfulness metrics, while out-performing it in term of precision of class-specific features localization.