Skip to yearly menu bar Skip to main content


Poster

Visualizing the Emergence of Intermediate Visual Patterns in DNNs

Mingjie Li · Shaobo Wang · Quanshi Zhang

Keywords: [ Deep Learning ] [ Adversarial Robustness and Security ]


Abstract:

This paper proposes a method to visualize the discrimination power of intermediate-layer visual patterns encoded by a DNN. Specifically, we visualize (1) how the DNN gradually learns regional visual patterns in each intermediate layer during the training process, and (2) the effects of the DNN using non-discriminative patterns in low layers to construct disciminative patterns in middle/high layers through the forward propagation. Based on our visualization method, we can quantify knowledge points (i.e. the number of discriminative visual patterns) learned by the DNN to evaluate the representation capacity of the DNN. Furthermore, this method also provides new insights into signal-processing behaviors of existing deep-learning techniques, such as adversarial attacks and knowledge distillation.

Chat is not available.