A Framework using Contrastive Learning for Classification with Noisy Labels

We propose a framework using contrastive learning as a pre-training task to perform image classification in the presence of noisy labels. Recent strategies such as pseudo-labelling, sample selection with Gaussian Mixture models, weighted supervised contrastive learning have been combined into a fine-tuning phase following the pre-training. This paper provides an extensive empirical study showing that a preliminary contrastive learning step brings a significant gain in performance when using different loss functions: non robust, robust, and early-learning regularized. Our experiments performed on standard benchmarks and real-world datasets demonstrate that: i) the contrastive pretraining increases the robustness of any loss function to noisy labels and ii) the additional fine-tuning phase can further improve accuracy, but at the cost of additional complexity.