State-Relabeling Adversarial Active Learning

Abstract

Active learning is to design label-efficient algorithms by sampling the most representative samples to be labeled by an oracle. In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and the labeled/unlabeled state information for deriving the most informative unlabeled samples. The SRAAL consists of a representation generator and a state discriminator. The generator uses the complementary annotation information with traditional reconstruction information to generate the unified representation of samples, which embeds the semantic into the whole data representation. Then, we design an online uncertainty indicator in the discriminator, which endues unlabeled samples with different importance. As a result, we can select the most informative samples based on the discriminator's predicted state. We also design an algorithm to initialize the labeled pool, which makes subsequent sampling more efficient. The experiments conducted on various datasets show that our model outperforms the previous state-of-art active learning methods and our initially sampling algorithm achieves better performance.

arXiv commentAccepted as Oral at CVPR 2020

References in corpus (6)

• Conditional Generative Adversarial Nets
• Adversarial Active Learning for Deep Networks: a Margin Based Approach
• Generative Adversarial Active Learning
• Cost-Effective Active Learning for Melanoma Segmentation
• Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes
• Gradient-free Policy Architecture Search and Adaptation