Research map / Detection and segmentation / Open-set and few-shot detection
Exploring Categorical Regularization for Domain Adaptive 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 |
|---|---|---|---|
| Add ICR to DA-Faster (ablation) | DA-Faster · Foggy Cityscapes val | mAP: 28.5 -> 29.4 | Helped |
| Add CCR to DA-Faster-ICR (ablation) | DA-Faster-ICR · Foggy Cityscapes val | mAP: 29.4 -> 29.9 | Helped |
| Add ICR to SW-Faster (ablation) | SW-Faster · Foggy Cityscapes val | mAP: 34.8 -> 36.5 | Helped |
| Add CCR to SW-Faster-ICR (ablation) | SW-Faster-ICR · Foggy Cityscapes val | mAP: 36.5 -> 37.4 | Helped |
| Add ICR to DA-Faster (ablation) | DA-Faster · BDD100k daytime val | mAP: 24.0 -> 24.7 | Helped |
| Add CCR to DA-Faster-ICR (ablation) | DA-Faster-ICR · BDD100k daytime val | mAP: 24.7 -> 25.3 | Helped |
| Add ICR to SW-Faster (ablation) | SW-Faster · BDD100k daytime val | mAP: 25.3 -> 26.4 | Helped |
| Add CCR to SW-Faster-ICR (ablation) | SW-Faster-ICR · BDD100k daytime val | mAP: 26.4 -> 26.9 | Helped |
| Add ICR to DA-Faster (ablation) | DA-Faster · Clipart1k | mAP: 34.7 -> 35.9 | Helped |
| Add CCR to DA-Faster-ICR (ablation) | DA-Faster-ICR · Clipart1k | mAP: 35.9 -> 36.7 | Helped |
| Add ICR to SW-Faster (ablation) | SW-Faster · Clipart1k | mAP: 36.8 -> 37.7 | Helped |
| Add CCR to SW-Faster-ICR (ablation) | SW-Faster-ICR · Clipart1k | mAP: 37.7 -> 38.3 | Helped |
Closest papers by meaning
- Domain Adaptive Faster R-CNN for Object Detection in the Wild (CVPR 2018 · similarity 0.92)
- Domain-Specific Suppression for Adaptive Object Detection (CVPR 2021 · similarity 0.91)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.90)
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.89)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.88)
- Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection (NeurIPS 2024 · similarity 0.88)
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.