You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: README.md
+15-14
Original file line number
Diff line number
Diff line change
@@ -1,14 +1,15 @@
1
1
# Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
2
2
3
-
The code repository for "[Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions](https://arxiv.org/abs/1812.03664)" (Accepted by CVPR 2020) in PyTorch. If you use any content of this repo for your work, please cite the following bib entry:
3
+
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions" [[paper]](https://openaccess.thecvf.com/content_CVPR_2020/papers/Ye_Few-Shot_Learning_via_Embedding_Adaptation_With_Set-to-Set_Functions_CVPR_2020_paper.pdf)[[ArXiv]](https://arxiv.org/abs/1812.03664)[[slides]](https://drive.google.com/file/d/17LpnSuT-fy-Je7hWxHV7o61jVFDQf3TK/view?usp=sharing)[[poster]](https://drive.google.com/file/d/1R4_eoxI9VrfUMzgcoBG9veJG2fhhQzxi/view?usp=sharing) (Accepted by CVPR 2020) in PyTorch. If you use any content of this repo for your work, please cite the following bib entry:
4
4
5
5
@inproceedings{ye2020fewshot,
6
6
author = {Han-Jia Ye and
7
7
Hexiang Hu and
8
8
De-Chuan Zhan and
9
9
Fei Sha},
10
10
title = {Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions},
11
-
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
11
+
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
12
+
pages = {8808--8817},
12
13
year = {2020}
13
14
}
14
15
@@ -23,23 +24,23 @@ We propose a novel model-based approach to adapt the instance embeddings to the
23
24
Experimental results on few-shot learning datasets with ResNet-12 backbone (Same as [this repo](https://github.com/kjunelee/MetaOptNet)). We report average results with 10,000 randomly sampled few-shot learning episodes for stablized evaluation.
24
25
25
26
**MiniImageNet Dataset**
26
-
| Setups | 1-Shot 5-Way | 5-Shot 5-Way | Link to Weights |
0 commit comments