Open AccessCross-domain few-shot classification through feature confusion
Author(s) -
Guoxiang Ye,
Yan Xia,
Zhangwei Feng,
Feng Tian
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1550/3/032025
Subject(s) - domain adaptation , computer science , domain (mathematical analysis) , focus (optics) , artificial intelligence , confusion , feature (linguistics) , machine learning , set (abstract data type) , training set , shot (pellet) , pattern recognition (psychology) , data mining , mathematics , classifier (uml) , psychology , mathematical analysis , linguistics , philosophy , physics , chemistry , organic chemistry , psychoanalysis , optics , programming language
Few-shot classification has made great progress in recent years which aims to solve new tasks using the prior knowledge obtained from a set of similar tasks with few labeled examples. However, the performance of current methods drops when domain shift exists between training and testing samples. Considering the situation where target domain examples are hard to collect, it is necessary to focus on the cross-domain problem. In this paper, we propose a simple method which embeds the domain adaptation method into the few-shot problem under a novel cross-domain few-shot setting, and focus on supervised setting in the target domain where few labeled data available for domain adaptation. Extensive empirical evidence shows the effectiveness of our method.