Label distribution based facial attractiveness computation by deep\n residual learning

2016/09/02 by Shu Liu, Bo Li, Liu, Shu +7 · 6 citations
Computer Science · Psychology · #Computer Vision and Pattern Recognition (cs.CV) #Evolutionary Psychology and Human Behavior #FOS: Computer and information sciences #Face and Expression Recognition #Face recognition and analysis

paper · pdf · doi:10.48550/arxiv.1609.00496

openalex publication_date 2016/09/02 · openalex created_date 2022/11/26 · openalex updated_date 2026/07/28

Abstract

Two challenges lie in the facial attractiveness computation research: the\nlack of true attractiveness labels (scores), and the lack of an accurate face\nrepresentation. In order to address the first challenge, this paper recasts\nfacial attractiveness computation as a label distribution learning (LDL)\nproblem rather than a traditional single-label supervised learning task. In\nthis way, the negative influence of the label incomplete problem can be\nreduced. Inspired by the recent promising work in face recognition using deep\nneural networks to learn effective features, the second challenge is expected\nto be solved from a deep learning point of view. A very deep residual network\nis utilized to enable automatic learning of hierarchical aesthetics\nrepresentation. Integrating these two ideas, an end-to-end deep learning\nframework is established. Our approach achieves the best results on a standard\nbenchmark SCUT-FBP dataset compared with other state-of-the-art work.\n

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition

Cited by

• VM-BeautyNet: A Synergistic Ensemble of Vision Transformer and Mamba for Facial Beauty Prediction
• FairViT-GAN: A Hybrid Vision Transformer with Adversarial Debiasing for Fair and Explainable Facial Beauty Prediction
• SynergyNet: Fusing Generative Priors and State-Space Models for Facial Beauty Prediction
• Scale-interaction transformer: a hybrid cnn-transformer model for facial beauty prediction
• Mamba-CNN: A Hybrid Architecture for Efficient and Accurate Facial Beauty Prediction
• Generative Pre-training for Subjective Tasks: A Diffusion Transformer-Based Framework for Facial Beauty Prediction

Related

• Lightweight Facial Attractiveness Prediction Using Dual Label Distribution
• A new humanlike facial attractiveness predictor with cascaded fine-tuning deep learning model
• Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation
• Understanding Beauty via Deep Facial Features
• Ethically aligned Deep Learning: Unbiased Facial Aesthetic Prediction