An Applicative Survey on Few-shot Learning

Background: Learning discriminative representation from large-scale data sets has made a breakthrough in decades. However, it is still a thorny problem to generate representative embedding from limited examples, for example, a class containing only one image. Recently, deep learn-ing-based Few-Shot Learning (FSL) has been proposed. It tackles this problem by leveraging prior knowledge in various ways. Objective: In this work, we review recent advances of FSL in a perspective of high-dimensional representation learning. The results of the analysis can provide insights and directions for future work. Methods: We first present the definition of general FSL. Then, we propose a general framework for the FSL problem and give the taxonomy under the framework. We survey two FSL directions: learning policy and meta-learning. Results: We review the advanced applications of FSL, including image classification, object detec-tion, image segmentation and other tasks etc., as well as the corresponding benchmarks to provide an overview of recent progress. Conclusion: In future work, FSL needs to be further studied in medical images, language models and reinforcement learning. In addition, cross-domain FSL, successive FSL and associated FSL are more challenging and valuable research directions. © 2022 Bentham Science Publishers.