Enhancing Performance of Occlusion-Based Explanation Methods by a Hierarchical Search Method on Input Images

Abstract

In this work, we address some drawbacks of back-propagation-based and perturbation-based visualization methods by proposing an explanation method called Fast Multi-resolution Occlusion (FMO). FMO, opposite to the back-propagation-based methods that cannot be applied on all types of Convolutional Neural Networks (CNNs), can highlight the important input features independent of the architecture. Also, FMO introduces a novel fast occlusion strategy called multi-resolution occlusion which not only efficiently addresses the time-consumption issue of the traditional Occlusion Test method but also outperforms the well-known perturbation-based methods. We assess the methods on CNNs DenseNet121, InceptionV3, InceptionResnetV2, MobileNet, and ResNet50 using three datasets ILSVRC2012, PASCAL VOC07, and COCO14.