Research map / Label-efficient and robust learning / Recognition and long-tail
Explanations for Occluded Images
Hana Chockler, Daniel Kroening, Youcheng Sun
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 |
|---|---|---|---|
| use causal-responsibility explanations instead of SBFL-based ranking | DC-Causal · MS-COCO partially occluded images | explanation size (% of pixels): 37.8 -> 13 | Improved |
| use causal ranking instead of DC-SBFL when keeping 20% of pixels | DC-Causal · MS-COCO partially occluded images | correct classification (%): 80% correct; more than 20% improvement over DC-SBFL | Improved |
| use DC-Causal instead of RISE | DC-Causal · Photo Bombing | explanations with no occlusion overlap: more than 60%, 20% better than RISE | Improved |
| vary the masking color from black to white (ablation) | DC-Causal · Photo Bombing | mean intersection with occlusions: influence less than 4% | No clear effect |
| use DC-Causal instead of RISE on explanation size | DC-Causal · Photo Bombing | explanation overlap with occlusion: smaller explanations but higher overlap with occlusions than RISE | Mixed |
Closest papers by meaning
- Generative causal explanations of black-box classifiers (NeurIPS 2020 · similarity 0.88)
- Explanation-based Data Augmentation for Image Classification (NeurIPS 2021 · similarity 0.87)
- Global Explanations for Image Classifiers (Student Abstract) (AAAI 2023 · similarity 0.87)
- Gradient-Based Instance-Specific Visual Explanations for Object Specification and Object Discrimination (TPAMI 2024 · similarity 0.86)
- ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection (ICLR 2023 · similarity 0.86)
- Rethinking Visual Counterfactual Explanations Through Region Constraint (ICLR 2025 · 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.
