Feature-map-level Online Adversarial Knowledge Distillation

Inseop Chung, SeongUk Park, Jangho Kim, Nojun Kwak

Keywords: Computer vision, Image classification, Knowledge distillation, Deep Learning

TL;DR: Online knowledge distillation method using feature map information.

Abstract: Feature maps contain rich information about image intensity and spatial correlation. However, previous online knowledge distillation methods only utilize the class probabilities. Thus in this paper, we propose an online knowledge distillation method that transfers not only the knowledge of the class probabilities but also that of the feature map using the adversarial training framework. We train multiple networks simultaneously by employing discriminators to distinguish the feature map distributions of different networks. Each network has its corresponding discriminator which discriminates the feature map from its own as fake while classifying that of the other network as real. By training a network to fool the corresponding discriminator, it can learn the other network’s feature map distribution. Discriminators and networks are trained concurrently in a minimax two-player game. Also, we propose a novel cyclic learning scheme for training more than two networks together. We have applied our method to various network architectures on the classification task and discovered a significant improvement of performance especially in the case of training a pair of a small network and a large one.