A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for…

• AG
  Australian Government

  Award: IC190100020
• QU
  Queensland University of Technology

  Award: IC190100020
• UO
  University of Queensland