A Technical Report for VIPriors Image Classification Challenge

TL;DR

This paper describes a method for image classification trained from scratch without pretraining, using strong backbones, multiple loss functions, augmentation strategies, and ensemble learning, achieving second place in the VIPriors challenge.

Contribution

It introduces a comprehensive approach combining advanced backbones, loss functions, augmentation, and ensemble techniques for scratch-trained image classification.

Findings

Achieved 70.15% Top-1 accuracy in VIPriors challenge

Utilized autoaugment and cutmix for better generalization

Ensemble learning improved model performance

Abstract

Image classification has always been a hot and challenging task. This paper is a brief report to our submission to the VIPriors Image Classification Challenge. In this challenge, the difficulty is how to train the model from scratch without any pretrained weight. In our method, several strong backbones and multiple loss functions are used to learn more representative features. To improve the models' generalization and robustness, efficient image augmentation strategies are utilized, like autoaugment and cutmix. Finally, ensemble learning is used to increase the performance of the models. The final Top-1 accuracy of our team DeepBlueAI is 0.7015, ranking second in the leaderboard.