Label distribution based facial attractiveness computation by deep residual learning

TL;DR

This paper introduces a deep residual learning framework that recasts facial attractiveness estimation as a label distribution learning problem, improving accuracy by addressing label ambiguity and leveraging hierarchical feature learning.

Contribution

It proposes a novel end-to-end deep residual network approach that combines label distribution learning with deep feature extraction for facial attractiveness prediction.

Findings

Achieved state-of-the-art results on SCUT-FBP dataset.

Reduced label ambiguity effects through label distribution learning.

Demonstrated effectiveness of deep residual networks in aesthetic feature learning.

Abstract

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.