Research map / Detection and segmentation / Weakly supervised detection and segmentation
DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection
Read the paperCheck 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 DETR-GA global aggregation with encoder class queries and a decoder foreground query | DN-DETR · PASCAL VOC → Clipart_all | mAP: 29.0% → 79.4% | Helped |
| Add DETR-GA global aggregation with encoder class queries and a decoder foreground query | DN-DETR · PASCAL VOC → Clipart_test | mAP: +28.6% | Helped |
| Add DETR-GA global aggregation with encoder class queries and a decoder foreground query | DN-DETR · PASCAL VOC → Watercolor | mAP: +17.8% | Helped |
| Add DETR-GA global aggregation with encoder class queries and a decoder foreground query | DN-DETR · PASCAL VOC → Comic | mAP: +28.1 | Helped |
| Add encoder class queries (ablation) | DETR-GA · PASCAL VOC → Clipart_test | mAP: +20.8% | Helped |
| Add decoder foreground query (ablation) | DETR-GA · PASCAL VOC → Clipart_test | mAP: +23.0% | Helped |
| Add common backbone practices to class queries and foreground query (ablation) | DETR-GA · PASCAL VOC → Clipart_test | mAP: +4.8 mAP | Helped |
| Add common backbone practices to class queries and foreground query (ablation) | DETR-GA · PASCAL VOC → Comic | mAP: 0.9 mAP | Helped |
| Use encoder class queries instead of average pooling for global aggregation (ablation) | DETR-GA encoder · PASCAL VOC → Clipart_test | mAP: 9.4 mAP | Helped |
| Add correlation between foreground query and object queries (ablation) | DETR-GA decoder · PASCAL VOC → Clipart_test | mAP: 2.1 | Helped |
| Remove position embedding from the foreground query (ablation) | DETR-GA decoder · PASCAL VOC → Clipart_test | mAP: 2.0 | Helped |
Closest papers by meaning
- Weakly Supervised Few-Shot Object Detection with DETR (AAAI 2024 · similarity 0.90)
- MS-DETR: Efficient DETR Training with Mixed Supervision (CVPR 2024 · similarity 0.89)
- MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism (CVPR 2025 · similarity 0.88)
- Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection (CVPR 2024 · similarity 0.88)
- Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers (ICML 2025 · similarity 0.87)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (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.