论文标题
毒蛇图像分类挑战的技术报告
A Technical Report for VIPriors Image Classification Challenge
论文作者
论文摘要
图像分类一直是一项艰巨而又具有挑战性的任务。本文是我们提交给Vipriors图像分类挑战的简短报告。在这一挑战中，困难是如何在没有任何审核重量的情况下从头开始训练模型。在我们的方法中，使用了一些强大的骨干和多个损失功能来学习更多代表性的特征。为了改善模型的概括和鲁棒性，使用了高效的图像增强策略，例如自动说明和cutmix。最后，合奏学习用于提高模型的性能。我们团队DeepBlueAi的最终前1位准确性为0.7015，排名排名第二。
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.
