AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Beyond Trivial Counterfactual Explanations With Diverse Valuable Explanations

Pau Rodríguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam Laradji, Laurent Charlin, David Vazquez

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 51 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Fisher-information masking of influential latent dimensions (ablation)DiVE · CelebA 'Young' classifiernon-trivial explanations (%): 43.51 -> 42.99No clear effect
add spectral clustering of the Fisher matrix (ablation)DiVE_Fisher · CelebA 'Young' classifiernon-trivial explanations (%): 42.99 -> 51.07Improved
add spectral clustering to DiVE (Fisher masking) (ablation)DiVE · CelebA 'Young' classifierattributes changed per explanation: 4.81 -> 4.58Improved
use disentangled beta-TCVAE backbone for xGEM+ (ablation)xGEM+ · CelebA 'Young' classifiernon-trivial explanations (%): 18.56 -> 34.62Improved
use beta-TCVAE backbone for xGEM+ (ablation)xGEM+ · CelebA 'Young' classifierattributes changed per explanation: 06.92 -> 06.70No clear effect
add perceptual reconstruction loss (ablation)DiVE · CelebA Smiling FID (Overall)FID: 55.9 -> 29.4Improved
add perceptual reconstruction loss (ablation)DiVE · CelebA Young FID (Overall)FID: 47.7 -> 33.8Improved
use DiVE instead of PEcounterfactual generation · CelebA Smiling FID (Overall)FID: 35.8 -> 29.4Improved
use DiVE instead of PEcounterfactual generation · CelebA Young FID (Overall)FID: 53.4 -> 33.8Improved
add Fisher information masking (ablation)DiVE · CelebA human evaluationreal non-trivial counterfactuals (%): 38.65 -> 40.56Improved
add spectral clustering of Fisher matrix (ablation)DiVE_Fisher · CelebA human evaluationreal non-trivial counterfactuals (%): 40.56 -> 41.90Improved
use DiVE instead of xGEM+bias detection · CelebA bias detection, f_biased, Smiling targetconfounding metric (overall): 0.29 -> 0.22Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy