AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks

Xue Wang, Zhibo Wang, Haiqin Weng, Hengchang Guo, Zhifei Zhang, Lu Jin, Tao Wei, Kui Ren

ICCV 2023 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 15 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
perturb target class while constraining non-target logits (CCE counterfactuals) instead of EP, PPE, PGD or Gaussian noiseCCE · ImageNet 2012 (ResNet-50)Class Deviation Score: 4.426 (EP) -> 5.959Improved
use CCE saliency instead of best baselines in insertion-deletion testssaliency explanation · ImageNet-compatible (ResNet-50)Insertion-Deletion difference: 39.95 -> 40.06Improved
CCE versus propagation-based GBP on deletion metricCCE · ImageNet-compatible (ResNet-50)Deletion: 10.72 (GBP) vs 17.96Hurt
mix positive and negative saliency maps (alpha=0.7) instead of positive only (ablation)CCE · ImageNet-compatible (ResNet-50)Insertion-Deletion difference: 39.33 -> 40.06Improved
mix positive and negative saliency maps instead of positive only (ablation)CCE · ImageNet-compatible (VGG-19)Insertion-Deletion difference: 40.07 -> 40.99Improved
present CCE explanations instead of GradCAM to usersexplanation interface · User study (100 participants)mean confidence rating: 4.022 -> 4.343Improved
run CCE explanation with sampled counterfactuals and noise instead of one-shot CECCE · ImageNet-compatiblerunning time: CCE takes about five times CE (0.93 s CE, 4.17 s CCE)Hurt
randomize model parameters cascade-wise (sanity check)CCE · ImageNet-compatible (VGG-19)SSIM of explanationsImproved

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