A Facial Expression Recognition Method Integrating Uncertainty Estimation and Active Learning
Source abstract
Abstract
The effectiveness of facial expression recognition (FER) algorithms hinges on the model’s quality and the availability of a substantial amount of labeled expression data. However, labeling large datasets demands significant... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Face and Expression Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (37)
Show source-provided references
1. Autism spectrum disorder detection: Video games based facial expression diagnosis using deep learning
2. Comparative analysis of emotional facial expression recognition and empathy in children with prader-willi syndrome and autism spectrum disorder10.1186/s40359-024-01590-3 ↗
3. A real-time automotive safety system based on advanced AI facial detection algorithms10.1109/TIV.2023.3272304 ↗
4. A survey on vision transformer10.1109/TPAMI.2022.3152247 ↗
5. Rethinking pseudo-labeling for semi-supervised facial expression recognition with contrastive self-supervised learning10.1109/ACCESS.2023.3274193 ↗
6. Face expression recognition based on NGO-BILSTM model10.3389/fnbot.2023.1155038 ↗
7. Self‐training maximum classifier discrepancy for EEG emotion recognition10.1049/cit2.12174 ↗
8. Wild facial expression recognition based on incremental active learning10.1016/j.cogsys.2018.06.017 ↗
9. Learning active learning from data
10. Bi3D: Bi-domain active learning for cross-domain 3D object detection
11. Active learning for deep visual tracking
12. How to measure uncertainty in uncertainty sampling for active learning10.1007/s10994-021-06003-9 ↗
13. GLISTER: Generalization based data subset selection for efficient and robust learning
14. A simple framework for contrastive learning of visual representations
15. MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels
16. Confident learning: Estimating uncertainty in dataset labels10.1613/jair.1.12125 ↗
17. Meta-Weight-Net: Learning an explicit mapping for sample weighting
18. Occluded facial expression recognition using self-supervised learning
19. Complexity aware center loss for facial expression recognition
20. Knowledge distillation meets self-supervision
21. To compress or not to compress—self-supervised learning and information theory: A review
22. Self-supervised learning: A succinct review10.1007/s11831-023-09884-2 ↗
23. A new active labeling method for deep learning
24. Speech emotion recognition using self-supervised features
25. D. Torpey and R. Klein, “DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning,” 2024, arXiv:2402.15598.10.1016/j.patrec.2024.09.005 ↗
26. Structural self-contrast learning based on adaptive weighted negative samples for facial expression recognition
27. Learning cognitive features as complementary for facial expression recognition
28. MDNN: Predicting student engagement via gaze direction and facial expression in collaborative learning
29. Human-computer interaction using deep fusion model-based facial expression recognition system
30. Facial expression recognition based on multi-channel attention residual network
31. J. T. Ashs, C. C. Zhang, A. Krishnamurthy, J. Langford, and A. Agarwal, “Deep batch active learning by diverse, uncertain gradient lower bounds,” 2019. Accessed: Feb. 24, 2020. [Online]. Available: https://arxiv.org/abs/1906.03671
32. O. Sener and S. Savarese, “Active learning for convolutional neural networks: A core-set approach,” 2017. Accessed: Jan. 1, 2018. [Online]. Available: https://arxiv.org/abs/1708.00489
33. Noise-tolerant paradigm for training face recognition CNNs
34. SphereFace: Deep hypersphere embedding for face recognition
35. Entropy-based active learning for object detection with progressive diversity constraint
36. Deep bayesian active learning with image data
37. Adversarial active learn-ing for deep networks: A margin based approach