Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose Estimation

TL;DR

This paper introduces a Keypoint Interactive Transformer (KIT) that learns structural dependencies among keypoints to improve general mammal pose estimation across diverse species with high appearance and pose variability.

Contribution

The paper proposes a novel KIT model with instance-level structure-supporting dependencies and a keypoint clustering method for body part bias, advancing general mammal pose estimation.

Findings

Effective handling of appearance and pose variances across species

Improved accuracy in mammal pose estimation tasks

Robustness to keypoint imbalance issues

Abstract

General mammal pose estimation is an important and challenging task in computer vision, which is essential for understanding mammal behaviour in real-world applications. However, existing studies are at their preliminary research stage, which focus on addressing the problem for only a few specific mammal species. In principle, from specific to general mammal pose estimation, the biggest issue is how to address the huge appearance and pose variances for different species. We argue that given appearance context, instance-level prior and the structural relation among keypoints can serve as complementary evidence. To this end, we propose a Keypoint Interactive Transformer (KIT) to learn instance-level structure-supporting dependencies for general mammal pose estimation. Specifically, our KITPose consists of two coupled components. The first component is to extract keypoint features and generate body part prompts. The features are supervised by a dedicated generalised heatmap regression loss (GHRL). Instead of introducing external visual/text prompts, we devise keypoints clustering to generate body part biases, aligning them with image context to generate corresponding instance-level prompts. Second, we propose a novel interactive transformer that takes feature slices as input tokens without performing spatial splitting. In addition, to enhance the capability of the KIT model, we design an adaptive weight strategy to address the imbalance issue among different keypoints.