期刊
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
卷 -, 期 -, 页码 3707-3716出版社
IEEE COMPUTER SOC
DOI: 10.1109/WACV51458.2022.00376
关键词
-
类别
资金
- MINECO, Spain [PID2019-104174GB-I00]
- CERCA Programme of Generalitat de Catalunya
- EU project CybSpeed [MSCA-RISE-2017-777720]
- CYTED Network [518RT0559]
In real-world scenarios, imbalanced class distribution in datasets further complicates the active learning process. To address this issue, we propose an optimization framework considering class-balancing, which can effectively improve the performance of active learning methods.
Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called long-tail distribution. We argue that this further complicates the active learning process, since the unbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we proposed a general optimization framework that explicitly takes class-balancing into account. Results on three datasets showed that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we showed that also on balanced datasets our method(1) generally results in a performance gain.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据