Region-adaptive concept aggregation for few-shot visual recognition
Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant informati...
Saved in:
Main Authors: | Han, Mengya, Zhan, Yibing, Yu, Baosheng, Luo, Yong, Hu, Han, Du, Bo, Wen, Yonggang, Tao, Dacheng |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/169205 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Towards a universal detector by mining concepts with small semantic gaps
by: Feng, J., et al.
Published: (2014) -
Document concept lattice for text understanding and summarization
by: Ye, S., et al.
Published: (2013) -
The professional self-concept of nurses: A review of the literature from 1992-2006
by: Arthur, D., et al.
Published: (2011) -
Learning concept bundles for video search with complex queries
by: Yuan, J., et al.
Published: (2013) -
A comprehensive representation scheme for video semantic ontology and its applications in semantic concept detection
by: Zha, Z.-J., et al.
Published: (2013)