Author:
Geng Xin,Smith-Miles Kate,Zhou Zhi-Hua
Abstract
One of the main difficulties in facial age estimation is the lack of sufficient training data for many ages. Fortunately, the faces at close ages look similar since aging is a slow and smooth process. Inspired by this observation, in this paper, instead of considering each face image as an example with one label (age), we regard each face image as an example associated with a label distribution. The label distribution covers a number of class labels, representing the degree that each label describes the example. Through this way, in addition to the real age, one face image can also contribute to the learning of its adjacent ages. We propose an algorithm named IIS-LLD for learning from the label distributions, which is an iterative optimization process based on the maximum entropy model. Experimental results show the advantages of IIS-LLD over the traditional learning methods based on single-labeled data.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Sample Topology Exploration for Label Distribution Learning;2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA);2023-10-09
2. Label-dependent feature exploration for label distribution learning;International Journal of Machine Learning and Cybernetics;2023-06-12
3. DAA: A Delta Age AdaIN operation for age estimation via binary code transformer;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06
4. Label distribution learning with high‐order label correlations;Concurrency and Computation: Practice and Experience;2023-04-12
5. Online label distribution learning based on kernel extreme learning machine;Proceedings of ELM 2021;2023