Research map / Detection and segmentation / Open-set and few-shot detection
MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised 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 category-wise discriminators with cosine-similarity memory-guided attention at conv5 (ablation) | Global domain adaptation (GDA) · Cityscapes → Foggy-Cityscapes | mAP: 36.2 -> 36.8 | Helped |
| Apply cosine-similarity category-wise adaptation at both conv4 and conv5 (ablation) | GDA+CDA+MA at conv5 · Cityscapes → Foggy-Cityscapes | mAP: 36.8 -> 40.0 | Helped |
| Use learned similarity instead of cosine similarity for attention (ablation) | GDA+CDA+MA at conv5 · Cityscapes → Foggy-Cityscapes | mAP: 36.8 -> 38.9 | Helped |
| Use learned similarity instead of cosine similarity with adaptation at conv4 and conv5 (ablation) | GDA+CDA+MA at conv4 and conv5 · Cityscapes → Foggy-Cityscapes | mAP: 40.0 -> 41.8 | Helped |
| Use MeGA-CDA instead of the strongest reported baseline | Object detector · Cityscapes → Foggy-Cityscapes | mAP: 39.3 -> 41.8 | Helped |
| Use MeGA-CDA instead of the strongest reported baseline | Object detector · Sim10K → Cityscapes | mAP: 43.0 -> 44.8 | Helped |
| Use MeGA-CDA instead of the strongest reported baseline | Object detector · KITTI → Cityscapes | mAP: 42.5 -> 43.0 | Helped |
| Use MeGA-CDA instead of the strongest reported baseline | Object detector · Cityscapes → KITTI | mAP: 73.5 -> 75.5 | Helped |
Closest papers by meaning
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.90)
- Category Dictionary Guided Unsupervised Domain Adaptation for Object Detection (AAAI 2021 · similarity 0.90)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.88)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.88)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · similarity 0.87)
- Category-Aware Active Domain Adaptation (ICML 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.