Error Understanding on CUB-200-2011

Metric: Average highest confidence (ResNet-101) (lower is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Average highest confidence (ResNet-101)▲	Extra Data	Paper	Date↕	Code
1	HSIC-Attribution	0.2493	No	Making Sense of Dependence: Efficient Black-box ...	2022-06-13	Code
2	Score-CAM	0.251	No	Score-CAM: Score-Weighted Visual Explanations fo...	2019-10-03	Code
3	Grad-CAM++	0.2647	No	Grad-CAM++: Improved Visual Explanations for Dee...	2017-10-30	Code
4	SMDL-Attribution (ICLR version)	0.4513	No	Less is More: Fewer Interpretable Region via Sub...	2024-02-14	Code

#1HSIC-AttributionSOTA
0.2493
Average highest confidence (ResNet-101)· 2022-06-13
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure Code
#2Score-CAMSOTA
0.251
Average highest confidence (ResNet-101)· 2019-10-03
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks Code
#3Grad-CAM++SOTA
0.2647
Average highest confidence (ResNet-101)· 2017-10-30
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks Code
#4SMDL-Attribution (ICLR version)
0.4513
Average highest confidence (ResNet-101)· 2024-02-14
Less is More: Fewer Interpretable Region via Submodular Subset Selection Code