Waterfall Transformer for Multi-person Pose Estimation

TL;DR

The paper introduces WTPose, a transformer-based framework for multi-person pose estimation that enhances feature representation through a waterfall module, outperforming existing transformer methods on COCO.

Contribution

It presents a novel Waterfall Transformer architecture that effectively captures multi-scale features for pose estimation in a single-pass, end-to-end trainable model.

Findings

Outperforms other transformer architectures on COCO dataset

Utilizes a waterfall module for multi-scale feature generation

Enhances receptive fields and context capturing capabilities

Abstract

We propose the Waterfall Transformer architecture for Pose estimation (WTPose), a single-pass, end-to-end trainable framework designed for multi-person pose estimation. Our framework leverages a transformer-based waterfall module that generates multi-scale feature maps from various backbone stages. The module performs filtering in the cascade architecture to expand the receptive fields and to capture local and global context, therefore increasing the overall feature representation capability of the network. Our experiments on the COCO dataset demonstrate that the proposed WTPose architecture, with a modified Swin backbone and transformer-based waterfall module, outperforms other transformer architectures for multi-person pose estimation