Research map / Label-efficient and robust learning / Recognition and long-tail
Soft Local Completeness: Rethinking Completeness in XAI
Ziv Weiss Haddad, Oren Barkan, Yehonatan Elisha, Noam Koenigstein
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 |
|---|---|---|---|
| monitor IDD per input and select the best explanation (SLOCm vs SLOC) (ablation) | SLOC · ImageNet val (DenseNet201) | IDD: 51.41 -> 56.4 | Improved |
| tune p dynamically per input instead of fixed per model (SLOC vs SLOCxp) (ablation) | SLOC · ImageNet val (ViT-S) | IDD: 53.33 -> 54.04 | Improved |
| use SLOC instead of LTX | Attribution methods · ImageNet val (ViT-S) | IDD: 40.27 -> 54.04 | Improved |
| use SLOC instead of LTX | Attribution methods · ImageNet val (DenseNet201) | NEG: 71.09 -> 70.97 | No clear effect |
| use SLOC on multi-object scenes | Attribution methods · Pascal VOC test (ViT-S) | IDD: 27.29 -> 39.5 (vs EP) | Improved |
| use SLOC on part-based FunnyBirds benchmark | Attribution methods · FunnyBirds (ResNet50) | overall score: 0.73 -> 0.78 (vs EP) | Improved |
| use SLOC instead of DIX on segmentation tests | Attribution methods · ImageNet-Seg (ResNet50) | mIoU: 0.66 -> 0.56 | Hurt |
| use SLOC instead of DIX on FunnyBirds with ViT-B | Attribution methods · FunnyBirds (ViT-B) | overall score: 0.87 -> 0.88 | No clear effect |
Closest papers by meaning
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.86)
- BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation (AAAI 2025 · similarity 0.86)
- Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics (NeurIPS 2024 · similarity 0.85)
- Even-if Explanations: Formal Foundations, Priorities and Complexity (AAAI 2025 · similarity 0.85)
- Saliency strikes back: How filtering out high frequencies improves white-box explanations (ICML 2024 · similarity 0.85)
- Evaluate with the Inverse: Efficient Approximation of Latent Explanation Quality Distribution (AAAI 2025 · similarity 0.84)
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.
