ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

TL;DR

This paper introduces ViTPose, a simple yet effective vision transformer-based model for human pose estimation, demonstrating high scalability, transferability, and state-of-the-art performance on the MS COCO benchmark.

Contribution

Proposes ViTPose, a plain vision transformer framework for pose estimation that is scalable, flexible, and achieves state-of-the-art results, revealing the potential of simple transformer structures.

Findings

ViTPose outperforms existing methods on MS COCO Keypoint Detection.

Large ViTPose models transfer knowledge effectively to smaller models.

Scaling up ViTPose improves performance and throughput.

Abstract

Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual recognition tasks. However, little effort has been made to reveal the potential of such simple structures for pose estimation tasks. In this paper, we show the surprisingly good capabilities of plain vision transformers for pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model called ViTPose. Specifically, ViTPose employs plain and non-hierarchical vision transformers as backbones to extract features for a given person instance and a lightweight decoder for pose estimation. It can be scaled up from 100M to 1B parameters by taking the advantages of the scalable model capacity and high parallelism of transformers, setting a new Pareto front between throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, pre-training and finetuning strategy, as well as dealing with multiple pose tasks. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our basic ViTPose model outperforms representative methods on the challenging MS COCO Keypoint Detection benchmark, while the largest model sets a new state-of-the-art. The code and models are available at https://github.com/ViTAE-Transformer/ViTPose.