A Technical Report for VIPriors Image Classification Challenge
This is an incremental improvement for a specific competition in image classification.
The paper tackled the VIPriors Image Classification Challenge by training models from scratch without pretrained weights, achieving a Top-1 accuracy of 0.7015 and ranking second.
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.