2nd Place Solution for ICCV 2021 VIPriors Image Classification Challenge: An Attract-and-Repulse Learning Approach

TL;DR

This paper introduces the Attract-and-Repulse framework, combining contrastive regularization, symmetric cross entropy, and mean teacher methods to improve small-scale image classification, achieving second place in a challenge.

Contribution

The novel Attract-and-Repulse framework effectively balances discriminative feature learning and overfitting prevention for small datasets.

Findings

Enhanced feature representations via contrastive regularization

Balanced class fitting with symmetric cross entropy

Improved performance through mean teacher calibration

Abstract

Convolutional neural networks (CNNs) have achieved significant success in image classification by utilizing large-scale datasets. However, it is still of great challenge to learn from scratch on small-scale datasets efficiently and effectively. With limited training datasets, the concepts of categories will be ambiguous since the over-parameterized CNNs tend to simply memorize the dataset, leading to poor generalization capacity. Therefore, it is crucial to study how to learn more discriminative representations while avoiding over-fitting. Since the concepts of categories tend to be ambiguous, it is important to catch more individual-wise information. Thus, we propose a new framework, termed Attract-and-Repulse, which consists of Contrastive Regularization (CR) to enrich the feature representations, Symmetric Cross Entropy (SCE) to balance the fitting for different classes and Mean Teacher to calibrate label information. Specifically, SCE and CR learn discriminative representations while alleviating over-fitting by the adaptive trade-off between the information of classes (attract) and instances (repulse). After that, Mean Teacher is used to further improve the performance via calibrating more accurate soft pseudo labels. Sufficient experiments validate the effectiveness of the Attract-and-Repulse framework. Together with other strategies, such as aggressive data augmentation, TenCrop inference, and models ensembling, we achieve the second place in ICCV 2021 VIPriors Image Classification Challenge.