Interpreting Pretext Tasks for Active Learning: A Reinforcement Learning Approach
Lists
Only you see this
Abstract
<title>Abstract</title> As the amount of labeled data increases, the performance of deep neural networks tends to improve. However, annotating a large volume of data can be expensive. Active learning addresses this challenge by selectively annotating unlabeled data. There have been recent attempts to incorporate self-supervised learning into active learning, but there are issues in utilizing the results of self-supervised learning, i.e., it is uncertain how these should be interpreted in the context of active learning. To address this issue, we propose a multi-armed bandit approach to handle the information provided by self-supervised learning in active learning. Furthermore, we devise a data sampling process so that reinforcement learning can be effectively performed. We evaluate the proposed method on various image classification benchmarks, including CIFAR-10, CIFAR-100, Caltech-101, SVHN, and ImageNet, where the proposed method significantly improves previous approaches.
BibTeX
@inproceedings{kim2024interpreting,
author = {Dongjoo Kim and Minsik Lee},
title = {{Interpreting Pretext Tasks for Active Learning: A Reinforcement Learning Approach}},
booktitle = {Scientific},
year = {2024},
doi = {10.1038/s41598-024-76864-2},
}Loading related content...