Y Tan, H Xia, S Song - The Visual Computer, 2024 - Springer
Label noise is inevitable in facial expression recognition (FER) datasets, especially for datasets that collected by web crawling, crowd sourcing in in-the-wild scenarios, which …
Supervised classification is a common field of machine learning. However, the existing classification methods based on deep models are vulnerable to overfitting the noisy labels in …
X Che, J Zhang, Z Qi, X Qi - arXiv preprint arXiv:2405.19606, 2024 - arxiv.org
Learning with noisy labels has become an effective strategy for enhancing the robustness of models, which enables models to better tolerate inaccurate data. Existing methods either …
S Wang, Y Huang - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Uncertainty in gaze estimation manifests in two aspects: 1) low-quality images caused by occlusion, blurriness, inconsistent eye movements, or even non-face images; 2) uncorrected …
S Dong, J Feng, D Fang - IEEE Journal of Selected Topics in …, 2024 - ieeexplore.ieee.org
Fine-grained ocean ship classification plays a crucial role in maritime military surveillance, traffic management, and antismuggling operations. However, the complex backgrounds of …
Spiking neural networks (SNNs) have garnered significant attention for their potential in ultra- low-power event-driven neuromorphic hardware implementations. One effective strategy for …
Q Wei, L Feng, H Wang, B An - arXiv preprint arXiv:2401.13360, 2024 - arxiv.org
Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a …
Y Zhou, X Li, F Liu, Q Wei, X Chen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Deep neural networks have shown great success in representation learning. Deep neural networks have shown great success in representation learning. However when learning with …
B Kim, BC Ko - 2024 International Conference on Electronics …, 2024 - ieeexplore.ieee.org
In real-world scenarios mirroring fine-grained datasets, labeling may result in noisy labels due to ambiguous data characteristics. This study introduces a new classification approach …