Research map / Label-efficient and robust learning / Recognition and long-tail
Better Understanding Differences in Attribution Methods via Systematic Evaluations
Sukrut Rao, Moritz Böhle, Bernt Schiele
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Gaussian smoothing to IntGrad attributions at the input layer | IntGrad · GridPG ImageNet VGG19 | Spearman correlation with Grad-CAM final layer: 0.34 -> 0.80 | Improved |
| add Gaussian smoothing to IxG with large kernels | IxG · GridPG Resnet152 | localization / correlation | No clear effect |
| use Gaussian smoothing instead of SmoothGrad noise averaging | IntGrad and IxG · GridPG ImageNet VGG11 / Resnet18 | localization score | Improved |
| add Gaussian smoothing to IntGrad and IxG | IntGrad and IxG · DiFull ImageNet | localization score | Hurt |
| apply LRP z+ rule to functionally equivalent transformed model | LRP z+ · DiFull VGG19 | attribution to disconnected regions | Hurt |
Closest papers by meaning
- Benchmarking the Attribution Quality of Vision Models (NeurIPS 2024 · similarity 0.92)
- How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations (ICLR 2025 · similarity 0.89)
- Pixel-level Certified Explanations via Randomized Smoothing (ICML 2025 · similarity 0.88)
- One Wave To Explain Them All: A Unifying Perspective On Feature Attribution (ICML 2025 · similarity 0.87)
- quanda: An Interpretability Toolkit for Training Data Attribution Evaluation (NeurIPS 2026 · similarity 0.87)
- LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions (CVPR 2025 · similarity 0.87)
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.
