Robust Noisy Label Learning via Two-Stream Sample Distillation
This addresses the problem of training robust deep learning models with noisy labels, which is critical for real-world applications, though it appears incremental as it builds on existing sample selection methods.
The paper tackles noisy label learning by proposing a two-stream sample distillation framework that extracts high-quality samples with clean labels, achieving state-of-the-art results on benchmark datasets like CIFAR-10, CIFAR-100, Tiny-ImageNet, and Clothing-1M.
Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning. Existing work either conducts sample selection or label correction to deal with noisy labels during the model training process. In this paper, we design a simple yet effective sample selection framework, termed Two-Stream Sample Distillation (TSSD), for noisy label learning, which can extract more high-quality samples with clean labels to improve the robustness of network training. Firstly, a novel Parallel Sample Division (PSD) module is designed to generate a certain training set with sufficient reliable positive and negative samples by jointly considering the sample structure in feature space and the human prior in loss space. Secondly, a novel Meta Sample Purification (MSP) module is further designed to mine adequate semi-hard samples from the remaining uncertain training set by learning a strong meta classifier with extra golden data. As a result, more and more high-quality samples will be distilled from the noisy training set to train networks robustly in every iteration. Extensive experiments on four benchmark datasets, including CIFAR-10, CIFAR-100, Tiny-ImageNet, and Clothing-1M, show that our method has achieved state-of-the-art results over its competitors.