Can I read Distilling Visual Priors from Self-Supervised Learning on EtoBox?

Distilling Visual Priors from Self-Supervised Learning by Zhao, Bingchen; Wen, Xin is a scholarly article available to read on EtoBox.

What is Distilling Visual Priors from Self-Supervised Learning about?

Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models for image classification under the data-deficient setting. The first phase is to learn a teacher model which possesses rich and generalizable visual representations via self-supervised learning, and the second phase is to distill the representations into a student model in a self-distillation manner, and meanwhile fine-tune the student model for the image classification task. We also propose a novel margin loss for the self-supervised contrastive learning proxy task to better learn the representation under the data-deficient scenario. Together with other tricks, we achieve competitive performance in the VIPriors image classification challenge.

Author

Zhao, Bingchen; Wen, Xin

Published

2020

Language

EN