A Two-Step Learning Method For Detecting Landmarks on Faces From Different Domains
This addresses the need for reduced annotation effort in facial landmark detection, particularly for animal faces, but is incremental as it builds on existing domain adaptation techniques.
The paper tackled the problem of detecting facial landmarks with limited annotated data by proposing a two-step domain adaptation method for human and animal faces, achieving better performance than state-of-the-art methods on datasets of cats, dogs, and horses.
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.