Active Semi-Supervised Learning by Exploring Per-Sample Uncertainty and Consistency

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of models at a lower cost, we propose a method called Active Semi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-03
Main Authors: Lim, Jaeseung, Jongkeun Na, Kwak, Nojun
Format: Article
Language:English
Subjects:
Data acquisition
Deep learning
Dynamic models
Model accuracy
Semi-supervised learning
Uncertainty
Unsupervised learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of models at a lower cost, we propose a method called Active Semi-supervised Learning (ASSL), which combines AL and SSL. To maximize the synergy between AL and SSL, we focused on the differences between ASSL and AL. ASSL involves more dynamic model updates than AL due to the use of unlabeled data in the training process, resulting in the temporal instability of the predicted probabilities of the unlabeled data. This makes it difficult to determine the true uncertainty of the unlabeled data in ASSL. To address this, we adopted techniques such as exponential moving average (EMA) and upper confidence bound (UCB) used in reinforcement learning. Additionally, we analyzed the effect of label noise on unsupervised learning by using weak and strong augmentation pairs to address datainconsistency. By considering both uncertainty and datainconsistency, we acquired data samples that were used in the proposed ASSL method. Our experiments showed that ASSL achieved about 5.3 times higher computational efficiency than SSL while achieving the same performance, and it outperformed the state-of-the-art AL method.
ISSN:2331-8422