Distilling base-and-meta network with contrastive learning for few-shot semantic segmentation

Distilling base-and-meta network with contrastive learning for few-shot semantic segmentation

Abstract Current studies in few-shot semantic segmentation mostly utilize meta-learning frameworks to obtain models that can be generalized to new categories. However, these models trained on base classes with sufficient annotated samples are biased towards these base classes, which results in seman...

Full description

Bibliographic Details
Main Authors: Xinyue Chen, Yueyi Wang, Yingyue Xu, Miaojing Shi
Format: Article
Language:English
Published: Springer 2023-11-01
Series:Autonomous Intelligent Systems
Subjects:
Semantic segmentation
Few-shot learning
Meta learning
Contrastive learning
Self-attention
Online Access:https://doi.org/10.1007/s43684-023-00058-2

Internet

https://doi.org/10.1007/s43684-023-00058-2

Similar Items