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...
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 |
Similar Items
-
Learning transferable cross-modality representations for few-shot hyperspectral and LiDAR collaborative classification
by: Mofan Dai, et al.
Published: (2024-02-01) -
CLIP-Driven Prototype Network for Few-Shot Semantic Segmentation
by: Shi-Cheng Guo, et al.
Published: (2023-09-01) -
Multi-Similarity Enhancement Network for Few-Shot Segmentation
by: Hao Chen, et al.
Published: (2023-01-01) -
Filtering Specialized Change in a Few-Shot Setting
by: Martin Hermann, et al.
Published: (2023-01-01) -
Automated Diagnosis of Major Depressive Disorder With Multi-Modal MRIs Based on Contrastive Learning: A Few-Shot Study
by: Tongtong Li, et al.
Published: (2024-01-01)