Pretrained equivariant features improve unsupervised landmark discovery

TL;DR

This paper introduces a two-step unsupervised landmark detection method that leverages pretrained equivariant features, significantly improving landmark discovery accuracy on challenging datasets.

Contribution

It reveals the limitations of current equivariance-based features and proposes a novel two-step approach using pretrained features for better landmark detection.

Findings

Achieves state-of-the-art results on BBC Pose and Cat-Head datasets.

Performs comparably on other benchmark datasets.

Highlights the importance of pretrained equivariant features in unsupervised learning.

Abstract

Locating semantically meaningful landmark points is a crucial component of a large number of computer vision pipelines. Because of the small number of available datasets with ground truth landmark annotations, it is important to design robust unsupervised and semi-supervised methods for landmark detection. Many of the recent unsupervised learning methods rely on the equivariance properties of landmarks to synthetic image deformations. Our work focuses on such widely used methods and sheds light on its core problem, its inability to produce equivariant intermediate convolutional features. This finding leads us to formulate a two-step unsupervised approach that overcomes this challenge by first learning powerful pixel-based features and then use the pre-trained features to learn a landmark detector by the traditional equivariance method. Our method produces state-of-the-art results in several challenging landmark detection datasets such as the BBC Pose dataset and the Cat-Head dataset. It performs comparably on a range of other benchmarks.