CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
Labels are costly and sometimes unreliable. Noisy label learning, semi-supervised learning, and contrastive learning are three different strategies for designing learning processes requiring less annotation cost. Semi-supervised learning and contrastive learning have been recently demonstrated to improve learning strategies that address datasets with noisy labels. Still, the inner connections between these fields as well as the potential to combine their strengths together have only started to emerge. In this paper, we explore further ways and advantages to fuse them. Specifically, we propose CSSL, a unified Contrastive Semi-Supervised Learning algorithm, and CoDiM (Contrastive DivideMix), a novel algorithm for learning with noisy labels. CSSL leverages the power of classical semi-supervised learning and contrastive learning technologies and is further adapted to CoDiM, which learns robustly from multiple types and levels of label noise. We show that CoDiM brings consistent improvements and achieves state-of-the-art results on multiple benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningImage ClassificationLearning with noisy labelsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rethinking Weak Supervision in Helping Contrastive Learning
Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noi…
Contrastive LearningDenoisingWeakly-supervised LearningContrastive Credibility Propagation for Reliable Semi-Supervised Learning
Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesome. Often, little is known about when and why an algorithm fails to outperform a supervised baseline. Using benchmark dat…
Pseudo LabelContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification …
Contrastive Learningimage-classificationImage ClassificationRepresentation Learning+2PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels
Large-scale image datasets frequently contain unavoidable noisy labels, resulting in overfitting in deep neural networks and declining performance. Most existing methods for learning from noisy labels operate as one-stag…
Image ClassificationLearning with noisy labelsGradient descent in higher codimension
We consider the behavior of gradient flow and of discrete and noisy gradient descent. It is commonly noted that the addition of noise to the process of discrete gradient descent can affect the trajectory of gradient desc…