Landmark Detection in Low Resolution Faces with Semi-Supervised Learning
This addresses a bottleneck for face recognition systems in low-resolution scenarios, though it is incremental as it adapts existing semi-supervised techniques to a specific data gap.
The paper tackles the problem of poor landmark detection on low-resolution face images by proposing a semi-supervised approach that learns from labeled high-resolution images, showing that direct prediction on low-resolution images improves face recognition performance compared to rescaling or superresolution methods.
Landmark detection algorithms trained on high resolution images perform poorly on datasets containing low resolution images. This deters the performance of algorithms relying on quality landmarks, for example, face recognition. To the best of our knowledge, there does not exist any dataset consisting of low resolution face images along with their annotated landmarks, making supervised training infeasible. In this paper, we present a semi-supervised approach to predict landmarks on low resolution images by learning them from labeled high resolution images. The objective of this work is to show that predicting landmarks directly on low resolution images is more effective than the current practice of aligning images after rescaling or superresolution. In a two-step process, the proposed approach first learns to generate low resolution images by modeling the distribution of target low resolution images. In the second stage, the roles of generated images and real low resolution images are switched and the model learns to predict landmarks for real low resolution images from generated low resolution images. With extensive experimentation, we study the impact of each of the design choices and also show that prediction of landmarks directly on low resolution images improves the performance of important tasks such as face recognition in low resolution images.