Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more data-hungry than common CNNs. They are often pretrained on JFT-300M or at least ImageNet and few works study training ViTs with limited data. In this paper, we investigate how to train ViTs with limited data (e.g., 2040 images). We give theoretical analyses that our method (based on parametric instance discrimination) is superior to other methods in that it can capture both feature alignment and instance similarities. We achieve state-of-the-art results when training from scratch on 7 small datasets under various ViT backbones. We also investigate the transferring ability of small datasets and find that representations learned from small datasets can even improve large-scale ImageNet training.

本篇研究介绍如何以有限数据训练Vision Transformers，并探讨使用基于参数实例鉴别方法的理论分析。结果表明，该方法优于其他方法，可捕捉特征对齐和实例相似性，并在多个ViT基础下从头开始训练7个小数据集，取得了最新的测试结果。此外，该研究还探讨了小型数据集的迁移能力，并发现从小型数据集中学习的表示甚至可以改善大规模ImageNet的训练结果。

用仅2040张图片训练视觉Transformer