SAST: a suppressing ambiguity self-training framework for facial expression recognition

被引:0
作者
Guo Z. [1 ]
Wei B. [1 ]
Liu X. [1 ]
Zhang Z. [1 ]
Liu S. [2 ]
Fan Y. [1 ]
机构
[1] School of Electronics and Information, Northwestern Polytechnical University, Xi’an
[2] Content Production Center of Virtual Reality, Beijing
基金
中国国家自然科学基金;
关键词
Facial expression recognition; Insufficient information; Self-training; Suppressing ambiguity;
D O I
10.1007/s11042-023-17749-w
中图分类号
学科分类号
摘要
Facial expression recognition (FER) suffers from insufficient label information, as human expressions are complex and diverse, with many expressions ambiguous. Using low-quality labels or low-quantity labels will aggravate ambiguity of model predictions and reduce the accuracy of FER. How to improve the robustness of FER to ambiguous data with insufficient information remains challenging. To this end, we propose the Suppressing Ambiguity Self-Training (SAST) framework which is the first attempt to address the problem of insufficient information both label quality and label quantity containing, simultaneously. Specifically, we design an Ambiguous Relative Label Usage (ARLU) strategy that mixes hard labels and soft labels to alleviate the information loss problem caused by hard labels. We also enhance the robustness of the model to ambiguous data by means of Self-Training Resampling (STR). We further use the landmarks and Patch Branch (PB) to enhance the ability of suppressing ambiguity. Experiments on RAF-DB, FERPlus, SFEW, and AffectNet datasets show that our SAST outperforms 6 semi-supervised methods with fewer annotations, and achieves competitive accuracy to State-Of-The-Art (SOTA) FER methods. Our code is available at https://github.com/Liuxww/SAST. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
引用
收藏
页码:56059 / 56076
页数:17
相关论文
共 49 条
[1]  
A medically assisted model for precise segmentation of osteosarcoma nuclei on pathological images, IEEE J Biomed Health Inform, (2023)
[2]  
Big data analytics on lung cancer diagnosis framework with deep learning, IEEE/ACM Trans Comput Biol Bioinform, (2023)
[3]  
Wu J., Xiao P., Huang H., Gou F., Zhou Z., Dai Z., An artificial intelligence multiprocessing scheme for the diagnosis of osteosarcoma mri images, IEEE J Biomed Health Inform, 26, 9, pp. 4656-4667, (2022)
[4]  
Wu J., Guo Y., Gou F., Dai Z., A medical assistant segmentation method for MRI images of osteosarcoma based on DecoupleSegNet, Int J Intell Syst, 37, 11, pp. 8436-8461, (2022)
[5]  
An attention–based ai–assisted segmentation system for osteosarcoma mri images, 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp. 1539-1543, (2022)
[6]  
Liang X., Xu L., Zhang W., Zhang Y., Liu J., Liu Z., A convolution-transformer dual branch network for head-pose and occlusion facial expression recognition, Vis Comput, 39, 2277, pp. 2637-2652, (2023)
[7]  
Joint pose and expression modeling for facial expression recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3359-3368, (2018)
[8]  
Suppressing Uncertainties for Large-Scale Facial Expression Recognition, pp. 6897-6906, (2020)
[9]  
Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition, pp. 6248-6257, (2021)
[10]  
Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression Recognition, pp. 13984-13993, (2020)