In the presence of noisy labels, designing robust loss functions is critical for securing the
generalization performance of deep neural networks. Cross Entropy (CE) loss has been …

Pre-training on large-scale datasets and then fine-tuning on downstream tasks have
become a standard practice in deep learning. However, pre-training data often contain label …

Foundation models are usually pre-trained on large-scale datasets and then adapted to
downstream tasks through tuning. However, the large-scale pre-training datasets, often …

In classification tasks with noisy labels, eliminating the interference of noisy label samples in
the dataset is the key to improving network performance. However, the distribution between …

Partial label learning (PLL) learns from training examples each associated with multiple
candidate labels, among which only one is valid. In recent years, benefiting from the strong …

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-
quality images, audios, and videos. They benefit significantly from extensive pre-training on …

We introduce a novel method for training machine learning models in the presence of noisy
labels, which are prevalent in domains such as medical diagnosis and autonomous driving …

Deep neural networks suffer from overfitting when training samples contain inaccurate
annotations (noisy labels), leading to suboptimal performance. In addressing this challenge …