Multi-Class Classification from Noisy-Similarity-Labeled Data
arXiv:2002.06508
Abstract
A similarity label indicates whether two instances belong to the same class while a class label shows the class of the instance. Without class labels, a multi-class classifier could be learned from similarity-labeled pairwise data by meta classification learning. However, since the similarity label is less informative than the class label, it is more likely to be noisy. Deep neural networks can easily remember noisy data, leading to overfitting in classification. In this paper, we propose a method for learning from only noisy-similarity-labeled data. Specifically, to model the noise, we employ a noise transition matrix to bridge the class-posterior probability between clean and noisy data. We further estimate the transition matrix from only noisy data and build a novel learning system to learn a classifier which can assign noise-free class labels for instances. Moreover, we theoretically justify how our proposed method generalizes for learning classifiers. Experimental results demonstrate the superiority of the proposed method over the state-of-the-art method on benchmark-simulated and real-world noisy-label datasets.
References in corpus (11)
- Understanding deep learning requires rethinking generalization
- Classification with Noisy Labels by Importance Reweighting
- Are Anchor Points Really Indispensable in Label-Noise Learning?
- Learning From Noisy Singly-labeled Data
- Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
- Neural network-based clustering using pairwise constraints
- Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
- Learning with Bounded Instance- and Label-dependent Label Noise
- Multi-class Classification without Multi-class Labels
- Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization