Research map / Detection and segmentation / CNN features
Black-Box Explanation of Object Detectors via Saliency Maps
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 black-box randomized masking weighted by detection similarity, including localization and category, instead of classification saliency baselines | YOLOv3 explanations · MS-COCO 2017 val | Pointing game (bbox): 0.7304 -> 0.9656 | Helped |
| Use black-box randomized masking weighted by detection similarity, including localization and category, instead of classification saliency baselines | YOLOv3 explanations · MS-COCO 2017 val | Pointing game (mask): 0.5195 -> 0.8458 | Helped |
| Use black-box randomized masking weighted by detection similarity, including localization and category, instead of classification saliency baselines | YOLOv3 explanations · MS-COCO 2017 val | Deletion: 0.0464 -> 0.0440 | Helped |
| Use black-box randomized masking weighted by detection similarity, including localization and category, instead of classification saliency baselines | YOLOv3 explanations · MS-COCO 2017 val | Insertion: 0.4561 -> 0.5622 | Helped |
| Show D-RISE explanations from the more accurate detector rather than the less accurate detector | YOLOv3 versus YOLOv3-Tiny · 242 objects on MS-COCO test | User preference for explanation being better or more trustworthy: 27.4% -> 50.2% | Helped |
Closest papers by meaning
- ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection (ICLR 2023 · similarity 0.89)
- Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects (CVPR 2018 · similarity 0.87)
- Weakly Supervised Salient Object Detection Using Image Labels (AAAI 2018 · similarity 0.86)
- DetKDS: Knowledge Distillation Search for Object Detectors (ICML 2024 · similarity 0.86)
- Interpreting Object-level Foundation Models via Visual Precision Search (CVPR 2025 · similarity 0.85)
- Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 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.