Skip to content

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, and weighted supervised contrastive learning have been combined into a fine-tuning phase following the pre-training. In this paper, we provide 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 pre-training 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.

Madalina Ciortan, Romain Dupuis and Thomas Peel, A Framework Using Contrastive Learning for Classification with Noisy Labels, Data, 2021, 6, 61.

DOI: https://doi.org/10.3390/data6060061

Watch the presentation on YouTube.

Public implementation: https://github.com/ciortanmadalina/constrastive-noisy-label

Click here to access the paper.

Share on linkedin
Share on twitter
Share on email

Releated Posts

Multimodal Classifier For Space Target Recognition

We propose a multi-modal framework to tackle the SPARK Challenge by classifying satellites using RGB and depth images. Our framework is mainly based on Auto-Encoders to embed the two modalities in a common latent space in order to exploit redundant and complementary information between the two types of data.
Read More

Advancing Innovation in Data Management

To build a data-driven economy across Europe and create a significant competitive advantage for European industry, companies will have to address the challenges in the data engineering and management domain. We are proud to partner with four top-class European institutions.
Read More