Distilling Visual Priors from Self-Supervised Learning
This addresses data deficiency in image classification, but it is incremental as it builds on existing self-supervised and distillation techniques.
The paper tackles overfitting in CNNs on small datasets by introducing a two-phase pipeline using self-supervised learning and knowledge distillation to improve generalization, achieving competitive performance in the VIPriors challenge.
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.