Research map / Label-efficient and robust learning / Recognition and long-tail
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
Robin Hesse, Simone Schaub-Meyer, Stefan Roth
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 |
|---|---|---|---|
| take absolute value of Integrated Gradients attribution (ablation) | Integrated Gradients · FunnyBirds, VGG16 | mean explainability score: 0.85 -> 0.83 | Hurt |
| take absolute value of IG: completeness versus contrastivity (ablation) | Integrated Gradients · FunnyBirds, VGG16 | completeness / contrastivity: completeness 0.95 -> 0.97; contrastivity 0.92 -> 0.84 | Mixed |
| remove bias term (X-DNN vs ResNet-50 with IG) (ablation) | ResNet-50 · FunnyBirds | completeness, correctness, contrastivity: completeness 0.86 -> 0.91; correctness 0.59 -> 0.6; contrastivity 0.98 -> 0.87 | Mixed |
| use B-cos network instead of standard ResNet-50 with IG | ResNet-50 · FunnyBirds | mean explainability score: 0.81 -> 0.82 | Improved |
| B-cos network effect on background independence | B-cos network · FunnyBirds | background independence: 1 -> 0.87 | Hurt |
| switch backbone from ResNet-50 to VGG16 for model-agnostic XAI methods | XAI methods · FunnyBirds | explanation scores: IG 0.81 -> 0.85 | Improved |
| use BagNet architecture whose structure matches attribution maps | BagNet · FunnyBirds | mean explainability score: 0.9 vs 0.86 (next best) | Improved |
| ProtoPNet prototypes as explanation | ProtoPNet · FunnyBirds | mean explainability score: 0.48 | Hurt |
| use coarser methods (Grad-CAM, RISE) instead of fine-grained gradient methods | Grad-CAM, RISE · FunnyBirds, ResNet-50 | completeness: IG 0.86 vs Grad-CAM 0.74 and RISE 0.7 | Hurt |
| use LIME as explanation method | LIME · FunnyBirds | correctness and contrastivity: 0 and 0 | Hurt |
Closest papers by meaning
- Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics (NeurIPS 2024 · similarity 0.87)
- Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ (Abstract Reprint) (AAAI 2024 · similarity 0.87)
- A Multimodal Automated Interpretability Agent (ICML 2024 · similarity 0.86)
- I-CEE: Tailoring Explanations of Image Classification Models to User Expertise (AAAI 2024 · similarity 0.85)
- F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI (ICLR 2025 · similarity 0.85)
- Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition (ICLR 2024 · similarity 0.85)
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.
