Domain adaption for few-shot learning in image classification

• Main Author: Pan, Yifei
• Other Authors: Mao Kezhi
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/164914
• Institution: Nanyang Technological University

Machine learning has been widely used in various fields and successfully addresses many image classification problems in the presence of sufficient samples, but performs poorly in the absence of samples. Few-shot learning is an innovative approach to solving this problem. In this article, I conduct a comprehensive survey and categorize few-shot learning algorithms from three perspectives: (i) initialization based methods; (ii) distance metric learning based methods; and (iii) hallucination based methods. I further study and evaluate (1) Fine-tuning; (2) Model-Agnostic Meta-Learning; (3) Prototypical Networks; (4) Relation Networks using the Omniglot and miniImageNet datasets.