Supervised deep learning has achieved tremendous success in speaker verification.
However, deep speaker models tend to overfit noisy labels when they are present in the …

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 …

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 …

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 …

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 …

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 …

Deep neural networks have shown great success in representation learning. Deep neural
networks have shown great success in representation learning. However when learning with …

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 …