Unsupervised Learning of Landmarks based on Inter-Intra Subject Consistencies
This addresses the problem of learning semantic landmarks without manual annotations for computer vision applications, but it is incremental as it builds on existing unsupervised approaches.
The paper tackles unsupervised landmark discovery in facial images by leveraging inter- and intra-subject consistencies, achieving better performance than previous state-of-the-art methods on MAFL and AFLW datasets.
We present a novel unsupervised learning approach to image landmark discovery by incorporating the inter-subject landmark consistencies on facial images. This is achieved via an inter-subject mapping module that transforms original subject landmarks based on an auxiliary subject-related structure. To recover from the transformed images back to the original subject, the landmark detector is forced to learn spatial locations that contain the consistent semantic meanings both for the paired intra-subject images and between the paired inter-subject images. Our proposed method is extensively evaluated on two public facial image datasets (MAFL, AFLW) with various settings. Experimental results indicate that our method can extract the consistent landmarks for both datasets and achieve better performances compared to the previous state-of-the-art methods quantitatively and qualitatively.