MobileFAN: Transferring Deep Hidden Representation for Face Alignment
This provides a more efficient solution for face alignment in applications like face analysis, though it is incremental as it builds on existing distillation and lightweight network techniques.
The paper tackles the problem of high memory cost in deep learning-based facial landmark detection by proposing MobileFAN, a lightweight model that achieves superior or equivalent performance with only 8% of the model size and lower computational cost compared to state-of-the-art methods.
Facial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a large number of parameters, resulting in high memory cost. In this paper, we aim for a lightweight as well as effective solution to facial landmark detection. To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder. The proposed MobileFAN, with only 8% of the model size and lower computational cost, achieves superior or equivalent performance compared with state-of-the-art models. Moreover, by transferring the geometric structural information of a face graph from a large complex model to our proposed MobileFAN through feature-aligned distillation and feature-similarity distillation, the performance of MobileFAN is further improved in effectiveness and efficiency for face alignment. Extensive experiment results on three challenging facial landmark estimation benchmarks including COFW, 300W and WFLW show the superiority of our proposed MobileFAN against state-of-the-art methods.