# Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation

arXiv: https://arxiv.org/abs/2007.01771 · HTML: https://mlsanity.com/paper/2007.01771/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning](https://mlsanity.com/paper/2504.07198/) (2025)
- [Lightweight Facial Attractiveness Prediction Using Dual Label Distribution](https://mlsanity.com/paper/2212.01742/) (2022)
- [General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone](https://mlsanity.com/paper/2307.10129/) (2023)
- [A Demographic Attribute Guided Approach to Age Estimation](https://mlsanity.com/paper/2205.10254/) (2022)
- [Uncertainty-Aware Remaining Lifespan Prediction from Images](https://mlsanity.com/paper/2506.13430/) (2025)

## Abstract (arXiv)

Facial attributes (eg, age and attractiveness) estimation performance has been greatly improved by using convolutional neural networks. However, existing methods have an inconsistency between the training objectives and the evaluation metric, so they may be suboptimal. In addition, these methods always adopt image classification or face recognition models with a large amount of parameters, which carry expensive computation cost and storage overhead. In this paper, we firstly analyze the essential relationship between two state-of-the-art methods (Ranking-CNN and DLDL) and show that the Ranking method is in fact learning label distribution implicitly. This result thus firstly unifies two existing popular state-of-the-art methods into the DLDL framework. Second, in order to alleviate the inconsistency and reduce resource consumption, we design a lightweight network architecture and propose a unified framework which can jointly learn facial attribute distribution and regress attribute value. The effectiveness of our approach has been demonstrated on both facial age and attractiveness estimation tasks. Our method achieves new state-of-the-art results using the single model with 36× fewer parameters and 3× faster inference speed on facial age/attractiveness estimation. Moreover, our method can achieve comparable results as the state-of-the-art even though the number of parameters is further reduced to 0.9M (3.8MB disk storage).