Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks

Understand

Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them.

• In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations.
• We interpret the model through average visualizations of this reduced set of features.
• Then, at test time, we explain the network prediction by accompanying the predicted class label with supporting visualizations derived from the identified features.