Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/RISE

RISE

Reported on 7 benchmarks across 2 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Image AttributiononVGGFace2
Insertion AUC score (ArcFace ResNet-101)· 2018-06-19
0.653
best: 0.6705 (SMDL-Attribution (ICLR version))
SOTA
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421
Image AttributiononCelebA
Insertion AUC score (ArcFace ResNet-101)· 2018-06-19
0.5703
best: 0.5752 (SMDL-Attribution (ICLR version))
SOTA
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421
Image AttributiononVGGFace2
Deletion AUC score (ArcFace ResNet-101)· 2018-06-19
0.1375
best: 0.3103 (Grad-CAM)
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421
Image AttributiononCUB-200-2011
Deletion AUC score (ResNet-101)· 2018-06-19
0.0665
best: 0.107 (LIME)
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421
Image AttributiononCUB-200-2011
Insertion AUC score (ResNet-101)· 2018-06-19
0.7193
best: 0.7262 (SMDL-Attribution (ICLR version))
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421
Image AttributiononCelebA
Deletion AUC score (ArcFace ResNet-101)· 2018-06-19
0.1444
best: 0.2865 (Grad-CAM)
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421

Miscellaneous1 result

Interpretability Techniques for Deep LearningonCelebA
Insertion AUC score· 2018-06-19
0.5703
SOTA
RISE: Randomized Input Sampling for Explanation of Black-box Models arXiv:1806.07421