Research map / Detection and segmentation / Open-set and few-shot detection
Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object Detection
Chaoqi Chen, Jiongcheng Li, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 PBGL (ablation) | DBGL (Faster R-CNN + ResNet-101) · VOC to Clipart1k | mAP (%): 39.5 -> 41.6 | Improved |
| add SBGL (ablation) | DBGL (Faster R-CNN + ResNet-101) · VOC to Clipart1k | mAP (%): 39.1 -> 41.6 | Improved |
| use mutual-nearest-neighbor pixel links instead of random links (ablation) | DBGL (Faster R-CNN + ResNet-101) · VOC to Clipart1k | mAP (%): 37.2 -> 41.6 | Improved |
| add node feature enhancement in SBGL (ablation) | DBGL (Faster R-CNN + ResNet-101) · VOC to Clipart1k | mAP (%): 41.0 -> 41.6 | Improved |
| add PBGL (ablation) | DBGL (Faster R-CNN + ResNet-101) · VOC to Watercolor2k | mAP (%): 52.0 -> 53.8 | Improved |
| add SBGL (ablation) | DBGL (Faster R-CNN + ResNet-101) · VOC to Comic2k | mAP (%): 27.6 -> 29.7 | Improved |
| use mutual-nearest-neighbor pixel links instead of random links (ablation) | DBGL (SSD + VGG-16) · VOC to Watercolor2k | mAP (%): 45.6 -> 52.0 | Improved |
| add PBGL (ablation) | DBGL (SSD + VGG-16) · VOC to Clipart1k | mAP (%): 36.1 -> 37.7 | Improved |
| add SBGL (ablation) | DBGL (SSD + VGG-16) · VOC to Clipart1k | mAP (%): 35.3 -> 37.7 | Improved |
| add node feature enhancement in SBGL (ablation) | DBGL (SSD + VGG-16) · VOC to Comic2k | mAP (%): 29.6 -> 30.4 | Improved |
| add PBGL (ablation) | DBGL (SSD + VGG-16) · VOC to Comic2k | mAP (%): 28.0 -> 30.4 | Improved |
| use mutual-nearest-neighbor pixel links instead of random links (ablation) | DBGL (SSD + VGG-16) · VOC to Clipart1k | mAP (%): 33.4 -> 37.7 | Improved |
Closest papers by meaning
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.91)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.91)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.90)
- Triple Feature Disentanglement for One-Stage Adaptive Object Detection (AAAI 2024 · similarity 0.90)
- Differential Alignment for Domain Adaptive Object Detection (AAAI 2025 · similarity 0.89)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.89)
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.
