Cross Modal Few-Shot Contextual Transfer for Heterogenous Image Classification

Deep transfer learning aims at dealing with challenges in new tasks with insufficient samples. However, when it comes to few-shot learning scenarios, due to the low diversity of several known training samples, they are prone to be dominated by specificity, thus leading to one-sidedness local feature...

Full description

Bibliographic Details
Main Authors: Zhikui Chen, Xu Zhang, Wei Huang, Jing Gao, Suhua Zhang
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-05-01
Series:Frontiers in Neurorobotics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnbot.2021.654519/full