BEiT
📌 核心贡献
将 BERT 的掩码语言建模迁移到视觉领域：用 DALL-E 的 dVAE 将图像离散化为 visual tokens，随机遮盖图像 patch 后让 ViT 预测对应的 visual token，实现视觉 BERT。在 ImageNet 分类和语义分割上超越监督预训练，是连接视觉量化 tokenizer 与表征学习的重要里程碑。
📖 摘要
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first “tokenize” the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at https://aka.ms/beit.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | Microsoft Research Asia |
| 发表 | 2021-06-15 |
| 分类 | cs.CV, cs.LG |
| 链接 | arXiv |
📝 我的笔记
ICLR 2022. 首次将 BERT masked prediction 应用于视觉 token 预测。