After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and video analysis. We offer three insights based on simple and easy to implement variants of vision transformers. (1) The residual layers of vision transformers, which are usually processed sequentially, can to some extent be processed efficiently in parallel without noticeably affecting the accuracy. (2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks. This saves compute, reduces the peak memory consumption at fine-tuning time, and allows sharing the majority of weights across tasks. (3) Adding MLP-based patch pre-processing layers improves Bert-like self-supervised training based on patch masking. We evaluate the impact of these design choices using the ImageNet-1k dataset, and confirm our findings on the ImageNet-v2 test set. Transfer performance is measured across six smaller datasets.

本文提出了三种易于实现的视觉 Transformer 变体。第一，可以在不降低精度的情况下并行处理视觉 Transformer 的残差层。第二，对注意力层的权重进行微调就足以适应更高分辨率和其他分类任务，这节省了计算量，减少了微调时的峰值内存消耗，并允许跨任务共享大部分权重。第三，添加基于 MLP 的补丁预处理层，可提高基于补丁掩模的 Bert 式自监督训练效果。作者使用 ImageNet-1k 数据集评估了这些设计选择的影响，并在 ImageNet-v2 测试集上确认了研究发现。文章在六个较小的数据集上评估了转移性能。

Vision Transformers 三要素