Generalized Few-Shot Classification on CUB-LT

Metric: Per-Class Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Per-Class Accuracy▼	Augmentations	Paper	Date↕	Code
1	DRAGON + Bal'Loss	60.1	No	From Generalized zero-shot learning to long-tail...	2020-04-05	Code
2	DRAGON	57.8	No	From Generalized zero-shot learning to long-tail...	2020-04-05	Code
3	LWS	53.1	No	Decoupling Representation and Classifier for Lon...	2019-10-21	Code
4	LDAM	50.1	No	Learning Imbalanced Datasets with Label-Distribu...	2019-06-18	Code
5	CADA-VAE	48.3	No	-	-	Code

#1DRAGON + Bal'LossSOTA
60.1
Per-Class Accuracy· 2020-04-05
From Generalized zero-shot learning to long-tail with class descriptors Code
#2DRAGON
57.8
Per-Class Accuracy· 2020-04-05
From Generalized zero-shot learning to long-tail with class descriptors Code
#3LWSSOTA
53.1
Per-Class Accuracy· 2019-10-21
Decoupling Representation and Classifier for Long-Tailed Recognition Code
#4LDAMSOTA
50.1
Per-Class Accuracy· 2019-06-18
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss Code
#5CADA-VAE
48.3
Per-Class Accuracy
No paperCode