Semantic Style Transfer for Enhancing Animal Facial Landmark Detection

TL;DR

This paper explores using semantic style transfer as a data augmentation technique to improve animal facial landmark detection, demonstrating enhanced robustness and accuracy in a case study with cats.

Contribution

It introduces a novel application of style transfer for data augmentation in animal landmark detection, including a method to mitigate annotation misalignment issues.

Findings

Style transfer on cropped facial images improves structural consistency.

Supervised Style Transfer retains up to 98% of baseline accuracy.

Augmentation with style-transferred images outperforms traditional methods.

Abstract

Neural Style Transfer (NST) is a technique for applying the visual characteristics of one image onto another while preserving structural content. Traditionally used for artistic transformations, NST has recently been adapted, e.g., for domain adaptation and data augmentation. This study investigates the use of this technique for enhancing animal facial landmark detectors training. As a case study, we use a recently introduced Ensemble Landmark Detector for 48 anatomical cat facial landmarks and the CatFLW dataset it was trained on, making three main contributions. First, we demonstrate that applying style transfer to cropped facial images rather than full-body images enhances structural consistency, improving the quality of generated images. Secondly, replacing training images with style-transferred versions raised challenges of annotation misalignment, but Supervised Style Transfer (SST) - which selects style sources based on landmark accuracy - retained up to 98% of baseline accuracy. Finally, augmenting the dataset with style-transferred images further improved robustness, outperforming traditional augmentation methods. These findings establish semantic style transfer as an effective augmentation strategy for enhancing the performance of facial landmark detection models for animals and beyond. While this study focuses on cat facial landmarks, the proposed method can be generalized to other species and landmark detection models.