DeepEMD : few-shot image classification with differentiable Earth Mover’s Distance and structured classifiers
In this paper, we address the few-shot classification task from a new perspective of optimal matching between image regions. We adopt the Earth Mover’s Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance. The EMD generates the...
Saved in:
Main Authors: | Zhang, Chi, Cai, Yujun, Lin, Guosheng, Shen, Chunhua |
---|---|
其他作者: | School of Computer Science and Engineering |
格式: | Conference or Workshop Item |
語言: | English |
出版: |
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/144270 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Efficient and effective similarity search over probabilistic data based on Earth Mover's Distance
由: Xu, J., et al.
出版: (2013) -
Face recognition using spatially constrained earth mover's distance
由: Xu, D., et al.
出版: (2014) -
SABRE: A Sensitive Attribute Bucketization and REdistribution framework for t-closeness
由: Cao, J., et al.
出版: (2013) -
Localized matching using Earth Mover's Distance towards discovery of common patterns from small image samples
由: TAN, Hung-Khoon, et al.
出版: (2009) -
Localized matching using Earth Mover's Distance towards discovery of common patterns from small image samples
由: TAN, Hung-Khoon, et al.
出版: (2009)