TACDFSL: Task Adaptive Cross Domain Few-Shot Learning

• Published in: Symmetry (Basel) Vol. 14; no. 6; p. 1097
• Main Authors: Zhang, Qi, Jiang, Yingluo, Wen, Zhijie
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.06.2022
• Subjects: Adaptation; Algorithms; Classification; Classifiers; cross domain few-shot learning; Datasets; domain shift; Domains; empirical marginal distribution; feature distribution transformation; Feature extraction; Image classification; Learning; Neural networks; Normal distribution
• ISSN: 2073-8994; 2073-8994
• DOI: 10.3390/sym14061097

Cross Domain Few-Shot Learning (CDFSL) has attracted the attention of many scholars since it is closer to reality. The domain shift between the source domain and the target domain is a crucial problem for CDFSL. The essence of domain shift is the marginal distribution difference between two domains which is implicit and unknown. So the empirical marginal distribution measurement is proposed, that is, WDMDS (Wasserstein Distance for Measuring Domain Shift) and MMDMDS (Maximum Mean Discrepancy for Measuring Domain Shift). Besides this, pre-training a feature extractor and fine-tuning a classifier are used in order to have a good generalization in CDFSL. Since the feature obtained by the feature extractor is high-dimensional and left-biased, the adaptive feature distribution transformation is proposed, to make the feature distribution of each sample be approximately Gaussian distribution. This approximate symmetric distribution improves image classification accuracy by 3% on average. In addition, the applicability of different classifiers for CDFSL is investigated, and the classification model should be selected based on the empirical marginal distribution difference between the two domains. The Task Adaptive Cross Domain Few-Shot Learning (TACDFSL) is proposed based on the above ideas. TACDFSL improves image classification accuracy by 3–9%.