Mining label-free consistency regularization for noisy facial expression recognition
Abstract Noisy labels are unavoidable in facial expression recognition (FER) task, significantly hindering FER performance in real-world scenarios. Recent advances tackle this problem by leveraging uncertainty for sample partitioning or constructing label distributions. However, these approaches pri...
Saved in:
Main Authors: | Yumei Tan, Haiying Xia, Shuxiang Song |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2024-12-01
|
Series: | Complex & Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1007/s40747-024-01722-7 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Partial Attention in Global Context and Local Interaction for Addressing Noisy Labels and Weighted Redundancies on Medical Images
by: Minh Tai Pham Nguyen, et al.
Published: (2024-12-01) -
Cyclic Learning Rate-Based Co-Training for Image Classification With Noisy Labels
by: Ying Zheng, et al.
Published: (2025-01-01) -
Learning with noisy labels via clean aware sharpness aware minimization
by: Bin Huang, et al.
Published: (2025-01-01) -
EEG emotion recognition based on parallel separable convolution and label smoothing regularization
by: Yong ZHANG, et al.
Published: (2023-05-01) -
Label credibility correction based on cell morphological differences for cervical cells classification
by: Wenbo Pang, et al.
Published: (2025-01-01)