Cargando…
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...
Autores principales: | Chen, Zhikui, Zhang, Xu, Huang, Wei, Gao, Jing, Zhang, Suhua |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8180855/ https://www.ncbi.nlm.nih.gov/pubmed/34108871 http://dx.doi.org/10.3389/fnbot.2021.654519 |
Ejemplares similares
-
Heterogeneous Ensemble-Based Spike-Driven Few-Shot Online Learning
por: Yang, Shuangming, et al.
Publicado: (2022) -
Boosting Knowledge Base Automatically via Few-Shot Relation Classification
por: Pang, Ning, et al.
Publicado: (2020) -
Feature fusion network based on few-shot fine-grained classification
por: Yang, Yajie, et al.
Publicado: (2023) -
Few-Shot Fine-Grained Image Classification via GNN
por: Zhou, Xiangyu, et al.
Publicado: (2022) -
Insights into few shot learning approaches for image scene classification
por: Soudy, Mohamed, et al.
Publicado: (2021)