Research map / Detection and segmentation / Open-set and few-shot detection
Multi-Granularity Alignment Domain Adaptation for 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 MGADA instead of CDG | Faster R-CNN with VGG-16 · Cityscapes to FoggyCityscapes | mAP: 42.3 -> 44.3 | Helped |
| use MGADA instead of CFA | FCOS with ResNet-101 · Cityscapes to FoggyCityscapes | mAP: 40.2 -> 43.8 | Helped |
| use MGADA instead of CFA | FCOS with VGG-16 · Sim10k to Cityscapes | mAP (car): 49.0 -> 54.6 | Helped |
| use MGADA instead of CFA | FCOS with ResNet-101 · KITTI to Cityscapes | mAP (car): 45.0 -> 46.5 | Helped |
| use MGADA instead of UMT | Faster R-CNN with ResNet-101 · PASCAL VOC to Clipart | mAP: 44.1 -> 44.8 | Helped |
| use MGADA instead of UMT | Faster R-CNN with ResNet-101 · PASCAL VOC to Watercolor | mAP: 58.1 -> 58.1 | No clear effect |
| add the category-level discriminator (ablation) | MGADA · Cityscapes to FoggyCityscapes | mAP: 39.3 -> 43.6 | Helped |
| add omni-scale gated fusion (ablation) | MGADA · Cityscapes to FoggyCityscapes | mAP: 41.3 -> 43.6 | Helped |
| replace average fusion with omni-scale gated fusion (ablation) | MGADA · Cityscapes to FoggyCityscapes | mAP: 42.1 -> 43.6 | Helped |
| replace 1x1 convolution fusion with omni-scale gated fusion (ablation) | MGADA · Cityscapes to FoggyCityscapes | mAP: 41.5 -> 43.6 | Helped |
| replace the baseline discriminator with a center-aware discriminator (ablation) | MGADA discriminator comparison · Cityscapes to FoggyCityscapes | mAP: 39.3 -> 40.5 | Helped |
| replace the baseline discriminator with a group discriminator (ablation) | MGADA discriminator comparison · Cityscapes to FoggyCityscapes | mAP: 39.3 -> 40.7 | Helped |
Closest papers by meaning
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.90)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.88)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.87)
- Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection (NeurIPS 2024 · similarity 0.87)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.87)
- Triple Feature Disentanglement for One-Stage Adaptive Object Detection (AAAI 2024 · similarity 0.87)
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.