Log In Sign Up

Semi-supervised learning by selective training with pseudo labels via confidence estimation

by   Masato Ishii, et al.

We propose a novel semi-supervised learning (SSL) method that adopts selective training with pseudo labels. In our method, we generate hard pseudo-labels and also estimate their confidence, which represents how likely each pseudo-label is to be correct. Then, we explicitly select which pseudo-labeled data should be used to update the model. Specifically, assuming that loss on incorrectly pseudo-labeled data sensitively increase against data augmentation, we select the data corresponding to relatively small loss after applying data augmentation. The confidence is used not only for screening candidates of pseudo-labeled data to be selected but also for automatically deciding how many pseudo-labeled data should be selected within a mini-batch. Since accurate estimation of the confidence is crucial in our method, we also propose a new data augmentation method, called MixConf, that enables us to obtain confidence-calibrated models even when the number of training data is small. Experimental results with several benchmark datasets validate the advantage of our SSL method as well as MixConf.


page 1

page 2

page 3

page 4


Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

We propose Dense FixMatch, a simple method for online semi-supervised le...

An analysis of over-sampling labeled data in semi-supervised learning with FixMatch

Most semi-supervised learning methods over-sample labeled data when cons...

Confidence-Guided Data Augmentation for Deep Semi-Supervised Training

We propose a new data augmentation technique for semi-supervised learnin...

Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning

Floods wreak havoc throughout the world, causing billions of dollars in ...

AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning

Semi-supervised learning (SSL) has recently proven to be an effective pa...

Labels, Information, and Computation: Efficient, Privacy-Preserving Learning Using Sufficient Labels

In supervised learning, obtaining a large set of fully-labeled training ...

Semi-Supervised Learning with Data Augmentation for End-to-End ASR

In this paper, we apply Semi-Supervised Learning (SSL) along with Data A...