تقرير
A Framework using Contrastive Learning for Classification with Noisy Labels
العنوان: | A Framework using Contrastive Learning for Classification with Noisy Labels |
---|---|
المؤلفون: | Ciortan, Madalina, Dupuis, Romain, Peel, Thomas |
سنة النشر: | 2021 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
الوصف: | 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-labeling, 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 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. Comment: 22 pages |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2104.09563 |
رقم الأكسشن: | edsarx.2104.09563 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |