← Search

Hao-Tian Li

2 accepted papers

2024

Vision-Language Models are Strong Noisy Label Detectors

NeurIPS 2024poster

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, th…

2023

Stochastic Feature Averaging for Learning with Long-Tailed Noisy Labels

IJCAI 2023poster

Deep neural networks have shown promising results on a wide variety of tasks using large-scale and well-annotated training datasets. However, data collected from real-world applications can suffer from two prevalent biases, i.e., long-tailed class distribution and label noise. Previous efforts on lo…