Bidirectional Uncertainty-Based Active Learning for Open Set Annotation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zong, Chen-Chen, Wang, Ye-Wen, Ning, Kun-Peng, Ye, Hai-Bo, Huang, Sheng-Jun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913576955936768
author Zong, Chen-Chen
Wang, Ye-Wen
Ning, Kun-Peng
Ye, Hai-Bo
Huang, Sheng-Jun
author_facet Zong, Chen-Chen
Wang, Ye-Wen
Ning, Kun-Peng
Ye, Hai-Bo
Huang, Sheng-Jun
contents Active learning (AL) in open set scenarios presents a novel challenge of identifying the most valuable examples in an unlabeled data pool that comprises data from both known and unknown classes. Traditional methods prioritize selecting informative examples with low confidence, with the risk of mistakenly selecting unknown-class examples with similarly low confidence. Recent methods favor the most probable known-class examples, with the risk of picking simple already mastered examples. In this paper, we attempt to query examples that are both likely from known classes and highly informative, and propose a Bidirectional Uncertainty-based Active Learning (BUAL) framework. Specifically, we achieve this by first pushing the unknown class examples toward regions with high-confidence predictions, i.e., the proposed Random Label Negative Learning method. Then, we propose a Bidirectional Uncertainty sampling strategy by jointly estimating uncertainty posed by both positive and negative learning to perform consistent and stable sampling. BUAL successfully extends existing uncertainty-based AL methods to complex open-set scenarios. Extensive experiments on multiple datasets with varying openness demonstrate that BUAL achieves state-of-the-art performance. The code is available at https://github.com/chenchenzong/BUAL.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15198
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bidirectional Uncertainty-Based Active Learning for Open Set Annotation
Zong, Chen-Chen
Wang, Ye-Wen
Ning, Kun-Peng
Ye, Hai-Bo
Huang, Sheng-Jun
Machine Learning
Active learning (AL) in open set scenarios presents a novel challenge of identifying the most valuable examples in an unlabeled data pool that comprises data from both known and unknown classes. Traditional methods prioritize selecting informative examples with low confidence, with the risk of mistakenly selecting unknown-class examples with similarly low confidence. Recent methods favor the most probable known-class examples, with the risk of picking simple already mastered examples. In this paper, we attempt to query examples that are both likely from known classes and highly informative, and propose a Bidirectional Uncertainty-based Active Learning (BUAL) framework. Specifically, we achieve this by first pushing the unknown class examples toward regions with high-confidence predictions, i.e., the proposed Random Label Negative Learning method. Then, we propose a Bidirectional Uncertainty sampling strategy by jointly estimating uncertainty posed by both positive and negative learning to perform consistent and stable sampling. BUAL successfully extends existing uncertainty-based AL methods to complex open-set scenarios. Extensive experiments on multiple datasets with varying openness demonstrate that BUAL achieves state-of-the-art performance. The code is available at https://github.com/chenchenzong/BUAL.
title Bidirectional Uncertainty-Based Active Learning for Open Set Annotation
topic Machine Learning
url https://arxiv.org/abs/2402.15198