Leveraging face-prior knowledge for general face representation learning
文献类型：期刊论文
| 作者 | Sun, Haomiao; He, Mingjie; Shan, Shiguang1; Han, Hu |
| 刊名 | PATTERN RECOGNITION
 |
| 出版日期 | 2025-12-01 |
| 卷号 | 168页码:8 |
| 关键词 | Face analysis General face representation learning Multi-level face-prior knowledge Auxiliary tasks |
| ISSN号 | 0031-3203 |
| DOI | 10.1016/j.patcog.2025.111784 |
| 英文摘要 | Face analysis, such as face attribute recognition and expression classification, has achieved remarkable progress via supervised deep learning methods. Although effective, supervised learning relies on a large amount of annotated data, which is labor-intensive. Besides, traditional models designed for individual tasks cannot generate a general facial representation that can be applied across multiple tasks. To address these issues, we present a novel general face representation learning method that empowers diverse face analysis tasks by incorporating auxiliary tasks with face-prior knowledge. Our approach employs three auxiliary tasks at pixel, patch, and component levels to exploit information from face images, enabling the model to learn multi-level face representations beneficial to diverse downstream tasks. We evaluate the efficacy of our approach on various downstream face analysis tasks, including facial action unit detection, expression classification, age estimation, and face attribute recognition. Specifically, our method surpasses the state-of-the-art by 3.5% for action unit detection and 1.53% for expression classification. On the AgeDB dataset, our method reduces the mean error by 0.64. Furthermore, in face attribute classification tasks, our model also achieves state-of-the-art performance. Experimental results also show that our proposed method outperforms previous methods under both full-shot and few-shot protocols. |
| 资助项目 | National Natural Science Foundation of China[U2336213] ; National Natural Science Foundation of China[62306298] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001502403800001 |
| 出版者 | ELSEVIER SCI LTD |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/42329]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Shan, Shiguang |
| 作者单位 | 1.Chinese Acad Sci, Inst Comp Technol, State Key Lab AI Safety, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Sun, Haomiao,He, Mingjie,Shan, Shiguang,et al. Leveraging face-prior knowledge for general face representation learning[J]. PATTERN RECOGNITION,2025,168:8. |
| APA | Sun, Haomiao,He, Mingjie,Shan, Shiguang,&Han, Hu.(2025).Leveraging face-prior knowledge for general face representation learning.PATTERN RECOGNITION,168,8. |
| MLA | Sun, Haomiao,et al."Leveraging face-prior knowledge for general face representation learning".PATTERN RECOGNITION 168(2025):8. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。