Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation

Abstract

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most samples as noisy and gradually decreases this selection rate during training. Such curriculum is sub-optimal since it does not consider the actual label noise rate in the training set. This paper addresses this issue with a new noise-rate estimation method that is easily integrated with most state-of-the-art (SOTA) LNL methods to produce a more effective curriculum. Synthetic and real-world benchmark results demonstrate that integrating our approach with SOTA LNL methods improves accuracy in most cases.

ECCV 2024

References in corpus (7)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
• Part-dependent Label Noise: Towards Instance-dependent Label Noise
• Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
• Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
• From BERT to GPT-3 Codex: Harnessing the Potential of Very Large Language Models for Data Management
• Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network