A Two-Step Learning Method For Detecting Landmarks on Faces From Different Domains

TL;DR

This paper introduces a two-step domain adaptation method for facial landmark detection that performs well across human and animal faces with limited annotated data, reducing the need for extensive labeling.

Contribution

The work proposes a novel two-step learning approach for cross-domain facial landmark detection, effective with minimal annotated data.

Findings

Outperforms state-of-the-art methods on multiple animal face datasets.

Requires fewer annotated samples to achieve high accuracy.

Effective for both human and animal face landmark detection.

Abstract

The detection of fiducial points on faces has significantly been favored by the rapid progress in the field of machine learning, in particular in the convolution networks. However, the accuracy of most of the detectors strongly depends on an enormous amount of annotated data. In this work, we present a domain adaptation approach based on a two-step learning to detect fiducial points on human and animal faces. We evaluate our method on three different datasets composed of different animal faces (cats, dogs, and horses). The experiments show that our method performs better than state of the art and can use few annotated data to leverage the detection of landmarks reducing the demand for large volume of annotated data.