Label distribution based facial attractiveness computation by deep residual learning
This work addresses facial attractiveness computation for computer vision applications, representing an incremental improvement by integrating existing techniques in a novel way.
The paper tackled facial attractiveness computation by addressing the lack of true labels and accurate face representation, recasting it as a label distribution learning problem and using a deep residual network to learn hierarchical aesthetics features, achieving the best results on the SCUT-FBP benchmark dataset.
Two challenges lie in the facial attractiveness computation research: the lack of true attractiveness labels (scores), and the lack of an accurate face representation. In order to address the first challenge, this paper recasts facial attractiveness computation as a label distribution learning (LDL) problem rather than a traditional single-label supervised learning task. In this way, the negative influence of the label incomplete problem can be reduced. Inspired by the recent promising work in face recognition using deep neural networks to learn effective features, the second challenge is expected to be solved from a deep learning point of view. A very deep residual network is utilized to enable automatic learning of hierarchical aesthetics representation. Integrating these two ideas, an end-to-end deep learning framework is established. Our approach achieves the best results on a standard benchmark SCUT-FBP dataset compared with other state-of-the-art work.