A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels

Abstract

The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and cheap to collect training images from the Web along with their noisy labels. This signifies the need of alternative approaches to training deep neural networks using such noisy labels. Existing methods tackling this problem either try to identify and correct the wrong labels or reweigh the data terms in the loss function according to the inferred noisy rates. Both strategies inevitably incur errors for some of the data points. In this paper, we contend that it is actually better to ignore the labels of some of the data points than to keep them if the labels are incorrect, especially when the noisy rate is high. After all, the wrong labels could mislead a neural network to a bad local optimum. We suggest a two-stage framework for the learning from noisy labels. In the first stage, we identify a small portion of images from the noisy training set of which the labels are correct with a high probability. The noisy labels of the other images are ignored. In the second stage, we train a deep neural network in a semi-supervised manner. This framework effectively takes advantage of the whole training set and yet only a portion of its labels that are most likely correct. Experiments on three datasets verify the effectiveness of our approach especially when the noisy rate is high.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Temporal Ensembling for Semi-Supervised Learning
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Training Convolutional Networks with Noisy Labels
• WebVision Database: Visual Learning and Understanding from Web Data
• Noise Tolerance under Risk Minimization
• Making Risk Minimization Tolerant to Label Noise
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Mixture Proportion Estimation via Kernel Embedding of Distributions
• Webly Supervised Learning of Convolutional Networks
• Learning from Noisy Labels with Distillation
• Learning From Noisy Large-Scale Datasets With Minimal Supervision
• Loss factorization, weakly supervised learning and label noise robustness
• Attend in groups: a weakly-supervised deep learning framework for learning from web data

Cited by in corpus (4)

• An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images
• Joint Negative and Positive Learning for Noisy Labels
• NLNL: Negative Learning for Noisy Labels
• Reliable Label Bootstrapping for Semi-Supervised Learning