Pose Recognition in the Wild: Animal pose estimation using Agglomerative Clustering and Contrastive Learning

TL;DR

This paper presents an unsupervised animal pose estimation method using edge detection, clustering, and contrastive learning, effectively recognizing multiple animal poses from unlabelled data and outperforming existing methods.

Contribution

The authors introduce a novel unsupervised architecture combining edge detection, agglomerative clustering, and contrastive learning for animal pose recognition from unlabelled data.

Findings

Outperforms state-of-the-art methods on TigDog and WLD datasets.

Effectively distinguishes animal body parts without labeled data.

Demonstrates strong generalization on other public datasets.

Abstract

Animal pose estimation has recently come into the limelight due to its application in biology, zoology, and aquaculture. Deep learning methods have effectively been applied to human pose estimation. However, the major bottleneck to the application of these methods to animal pose estimation is the unavailability of sufficient quantities of labeled data. Though there are ample quantities of unlabelled data publicly available, it is economically impractical to label large quantities of data for each animal. In addition, due to the wide variety of body shapes in the animal kingdom, the transfer of knowledge across domains is ineffective. Given the fact that the human brain is able to recognize animal pose without requiring large amounts of labeled data, it is only reasonable that we exploit unsupervised learning to tackle the problem of animal pose recognition from the available, unlabelled data. In this paper, we introduce a novel architecture that is able to recognize the pose of multiple animals fromunlabelled data. We do this by (1) removing background information from each image and employing an edge detection algorithm on the body of the animal, (2) Tracking motion of the edge pixels and performing agglomerative clustering to segment body parts, (3) employing contrastive learning to discourage grouping of distant body parts together. Hence we are able to distinguish between body parts of the animal, based on their visual behavior, instead of the underlying anatomy. Thus, we are able to achieve a more effective classification of the data than their human-labeled counterparts. We test our model on the TigDog and WLD (WildLife Documentary) datasets, where we outperform state-of-the-art approaches by a significant margin. We also study the performance of our model on other public data to demonstrate the generalization ability of our model.