BAL: Balancing Diversity and Novelty for Active Learning

Jingyao Li, Pengguang Chen, Shaozuo Yu, Shu Liu, Jiaya Jia

2023IEEE Transactions on Pattern Analysis and Machine Intelligence17 citationsDOI

Abstract

The objective of Active Learning is to strategically label a subset of the dataset to maximize performance within a predetermined labeling budget. In this study, we harness features acquired through self-supervised learning. We introduce a straightforward yet potent metric, Cluster Distance Difference, to identify diverse data. Subsequently, we introduce a novel framework, Balancing Active Learning (BAL), which constructs adaptive sub-pools to balance diverse and uncertain data. Our approach outperforms all established active learning methods on widely recognized benchmarks by 1.20%. Moreover, we assess the efficacy of our proposed framework under extended settings, encompassing both larger and smaller labeling budgets. Experimental results demonstrate that, when labeling 80% of the samples, the performance of the current SOTA method declines by 0.74%, whereas our proposed BAL achieves performance comparable to the full dataset.

Topics & Concepts

Computer scienceNoveltyMachine learningArtificial intelligenceMetric (unit)Active learning (machine learning)Labeled dataTraining setPerformance metricSemi-supervised learningEngineeringOperations managementEconomicsTheologyPhilosophyManagementMachine Learning and AlgorithmsDomain Adaptation and Few-Shot LearningMachine Learning and Data Classification