Lightweight Facial Attractiveness Prediction Using Dual Label Distribution

TL;DR

This paper introduces a lightweight, dual label distribution approach for facial attractiveness prediction that effectively utilizes dataset information and balances accuracy with efficiency using MobileNetV2.

Contribution

The paper proposes a novel end-to-end FAP method integrating dual label distribution and lightweight design, improving dataset utilization and model efficiency.

Findings

Achieves promising results on benchmark datasets.

Balances performance and computational efficiency.

Demonstrates the importance of designed learning modules.

Abstract

Facial attractiveness prediction (FAP) aims to assess facial attractiveness automatically based on human aesthetic perception. Previous methods using deep convolutional neural networks have improved the performance, but their large-scale models have led to a deficiency in flexibility. In addition, most methods fail to take full advantage of the dataset. In this paper, we present a novel end-to-end FAP approach that integrates dual label distribution and lightweight design. The manual ratings, attractiveness score, and standard deviation are aggregated explicitly to construct a dual-label distribution to make the best use of the dataset, including the attractiveness distribution and the rating distribution. Such distributions, as well as the attractiveness score, are optimized under a joint learning framework based on the label distribution learning (LDL) paradigm. The data processing is simplified to a minimum for a lightweight design, and MobileNetV2 is selected as our backbone. Extensive experiments are conducted on two benchmark datasets, where our approach achieves promising results and succeeds in balancing performance and efficiency. Ablation studies demonstrate that our delicately designed learning modules are indispensable and correlated. Additionally, the visualization indicates that our approach can perceive facial attractiveness and capture attractive facial regions to facilitate semantic predictions. The code is available at https://github.com/enquan/2D_FAP.