Interpretability Techniques for Deep Learning on CelebA

Metric: Insertion AUC score (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Insertion AUC score▼	Extra Data	Paper	Date↕	Code
1	RISE	0.5703	No	RISE: Randomized Input Sampling for Explanation ...	2018-06-19	Code
2	HSIC-Attribution	0.5692	No	Making Sense of Dependence: Efficient Black-box ...	2022-06-13	Code
3	Kernel SHAP	0.5246	No	A Unified Approach to Interpreting Model Predict...	2017-05-22	Code
4	LIME	0.5246	No	"Why Should I Trust You?": Explaining the Predic...	2016-02-16	Code
5	Saliency	0.4632	No	Deep Inside Convolutional Networks: Visualising ...	2013-12-20	Code
6	Grad-CAM	0.3721	No	Grad-CAM: Visual Explanations from Deep Networks...	2016-10-07	Code
7	Integrated Gradients	0.3578	No	Axiomatic Attribution for Deep Networks	2017-03-04	Code

#1RISESOTA
0.5703
Insertion AUC score· 2018-06-19
RISE: Randomized Input Sampling for Explanation of Black-box Models Code
#2HSIC-Attribution
0.5692
Insertion AUC score· 2022-06-13
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure Code
#3Kernel SHAP
0.5246
Insertion AUC score· 2017-05-22
A Unified Approach to Interpreting Model Predictions Code
#4LIMESOTA
0.5246
Insertion AUC score· 2016-02-16
"Why Should I Trust You?": Explaining the Predictions of Any Classifier Code
#5SaliencySOTA
0.4632
Insertion AUC score· 2013-12-20
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps Code
#6Grad-CAM
0.3721
Insertion AUC score· 2016-10-07
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization Code
#7Integrated Gradients
0.3578
Insertion AUC score· 2017-03-04
Axiomatic Attribution for Deep Networks Code