Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization

TL;DR

This paper introduces a two-stage framework for training neural networks with noisy labels, using instance-level difficulty modeling and dynamic loss weighting to improve accuracy and efficiency without extensive hyperparameter tuning.

Contribution

It proposes a novel dynamic optimization method with a simple metric for noise modeling, reducing computational costs and hyperparameter tuning in noisy label learning.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Reduces computational time by nearly 75%.

Enhances model scalability and robustness to label noise.

Abstract

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational costs, heavy hyperparameter tuning process, and coarse-grained optimization. To address these challenges, we propose a novel two-stage noisy learning framework that enables instance-level optimization through a dynamically weighted loss function, avoiding hyperparameter tuning. To obtain stable and accurate information about noise modeling, we introduce a simple yet effective metric, termed wrong event, which dynamically models the cleanliness and difficulty of individual samples while maintaining computational costs. Our framework first collects wrong event information and builds a strong base model. Then we perform noise-robust training on the base model, using a probabilistic model to handle the wrong event information of samples. Experiments on five synthetic and real-world LNL benchmarks demonstrate our method surpasses state-of-the-art methods in performance, achieves a nearly 75% reduction in computational time and improves model scalability.