Research map / Detection and segmentation / Weakly supervised detection and segmentation
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection
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 informative and consistent correspondence mining instead of the strongest listed baseline | Cross-domain weakly supervised object detection · Clipart1k | mAP: 40.3 -> 46.7 | Helped |
| Use informative and consistent correspondence mining instead of the strongest listed baseline | Cross-domain weakly supervised object detection · Watercolor2k | mAP: 53.3 -> 57.4 | Helped |
| Use informative and consistent correspondence mining instead of the strongest listed baseline | Cross-domain weakly supervised object detection · Comic2k | mAP: 32.9 -> 37.1 | Helped |
| Add pixel-wise informative correspondence mining (ablation) | Source-only Faster-RCNN · Clipart1k | mAP: 27.8 -> 44.3 | Helped |
| Add adversarial masking to ICM (ablation) | ICM on Faster-RCNN · Clipart1k | mAP: 44.3 -> 45.0 | Helped |
| Add consistent correspondence mining (ablation) | ICM on Faster-RCNN · Clipart1k | mAP | Helped |
| Add region offset regression (ablation) | ICM on Faster-RCNN · Clipart1k | mAP: 45.5 -> 46.7 | Helped |
Closest papers by meaning
- Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation (CVPR 2018 · similarity 0.92)
- DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection (CVPR 2023 · similarity 0.89)
- H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection (CVPR 2022 · similarity 0.89)
- Adapting Object Detectors via Selective Cross-Domain Alignment (CVPR 2019 · similarity 0.88)
- Cross Domain Object Detection by Target-Perceived Dual Branch Distillation (CVPR 2022 · similarity 0.87)
- Relational Matching for Weakly Semi-Supervised Oriented Object Detection (CVPR 2024 · similarity 0.86)
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.