Swin Transformer V2: Scaling Up Capacity and Resolution

TL;DR

This paper introduces Swin Transformer V2, a large-scale vision model with novel training techniques that improve stability, resolution transfer, and reduce data needs, achieving state-of-the-art results efficiently.

Contribution

It proposes new methods for training stability, resolution transfer, and self-supervised pre-training, enabling the training of the largest dense vision model to date with high efficiency.

Findings

Trained a 3 billion-parameter Swin Transformer V2 model.

Achieved new records on four major vision benchmarks.

Reduced training data and time by 40 times compared to previous models.

Abstract

Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images. Through these techniques, this paper successfully trained a 3 billion-parameter Swin Transformer V2 model, which is the largest dense vision model to date, and makes it capable of training with images of up to 1,536$\times$1,536 resolution. It set new performance records on 4 representative vision tasks, including ImageNet-V2 image classification, COCO object detection, ADE20K semantic segmentation, and Kinetics-400 video action classification. Also note our training is much more efficient than that in Google's billion-level visual models, which consumes 40 times less labelled data and 40 times less training time. Code is available at \url{https://github.com/microsoft/Swin-Transformer}.