2024
DOI: 10.1609/aaai.v38i4.28094
|View full text |Cite
|
Sign up to set email alerts
|

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

Jianwu Li,
Kaiyue Shi,
Guo-Sen Xie
et al.

Abstract: The goal of this paper is to alleviate the training cost for few-shot semantic segmentation (FSS) models. Despite that FSS in nature improves model generalization to new concepts using only a handful of test exemplars, it relies on strong supervision from a considerable amount of labeled training data for base classes. However, collecting pixel-level annotations is notoriously expensive and time-consuming, and small-scale training datasets convey low information density that limits test-time generalization. To… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
references
References 37 publications
0
0
0
Order By: Relevance