Semi-supervised Keypoint Localization

TL;DR

This paper introduces a semi-supervised method for keypoint localization that reduces labeling effort by learning from both labeled and unlabeled images, improving accuracy on animal and human benchmarks.

Contribution

It proposes a novel semi-supervised framework that learns keypoint heatmaps and pose-invariant representations using semantic consistency and data augmentation.

Findings

Outperforms previous methods on multiple benchmarks

Effectively reduces labeled data requirements

Achieves high accuracy in animal and human keypoint detection

Abstract

Knowledge about the locations of keypoints of an object in an image can assist in fine-grained classification and identification tasks, particularly for the case of objects that exhibit large variations in poses that greatly influence their visual appearance, such as wild animals. However, supervised training of a keypoint detection network requires annotating a large image dataset for each animal species, which is a labor-intensive task. To reduce the need for labeled data, we propose to learn simultaneously keypoint heatmaps and pose invariant keypoint representations in a semi-supervised manner using a small set of labeled images along with a larger set of unlabeled images. Keypoint representations are learnt with a semantic keypoint consistency constraint that forces the keypoint detection network to learn similar features for the same keypoint across the dataset. Pose invariance is achieved by making keypoint representations for the image and its augmented copies closer together in feature space. Our semi-supervised approach significantly outperforms previous methods on several benchmarks for human and animal body landmark localization.