Semantic input sampling for explanation (sise) of convolutional neural networks

Abstract

Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.