State-Relabeling Adversarial Active Learning
CVPR(2020)
摘要
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.
更多查看译文
关键词
state-relabeling adversarial active learning,label-efficient algorithms,representative samples,adversarial active learning model,SRAAL,informative unlabeled samples,representation generator,state discriminator,complementary annotation information,reconstruction information,unified representation,data representation,informative samples,labeled pool,subsequent sampling,sampling algorithm,online uncertainty indicator
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络