Research map / Detection and segmentation / CNN features
DA-DETR: Domain Adaptive Detection Transformer With Information Fusion
Jingyi Zhang, Jiaxing Huang, Zhipeng Luo, Gongjie Zhang, Xiaoqin Zhang, Shijian Lu
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 DA-DETR's CTBlender-based domain adaptation | Deformable-DETR · Cityscapes → Foggy Cityscapes | mAP: 28.5 -> 43.5 | Improved |
| add DA-DETR's CTBlender-based domain adaptation | Deformable-DETR · SIM 10k → Cityscapes | mAP on Car: 57.9 -> 54.7 | Hurt |
| add DA-DETR's CTBlender-based domain adaptation | Deformable-DETR · KITTI → Cityscapes | mAP on Car: 39.5 -> 48.9 | Improved |
| add DA-DETR's CTBlender-based domain adaptation | Deformable-DETR · PASCAL VOC → Clipart1k | mAP: 29.1 -> 41.3 | Improved |
| add DA-DETR's CTBlender-based domain adaptation | Deformable-DETR · PASCAL VOC → Watercolor2k | mAP: 36.2 -> 50.6 | Improved |
| add DA-DETR's CTBlender-based domain adaptation | Deformable-DETR · PASCAL VOC → Comic2k | mAP: 20.3 -> 35.1 | Improved |
| add direct adversarial feature alignment (ablation) | Deformable-DETR · Cityscapes → Foggy Cityscapes | mAP: 28.5 -> 38.4 | Improved |
| add splitting to Direct-align (ablation) | Direct-align · Cityscapes → Foggy Cityscapes | mAP: 38.4 -> 41.8 | Improved |
| add shuffling to Direct-align (ablation) | Direct-align · Cityscapes → Foggy Cityscapes | mAP: 38.4 -> 41.4 | Improved |
| add splitting and shuffling to Direct-align (ablation) | Direct-align · Cityscapes → Foggy Cityscapes | mAP: 38.4 -> 42.3 | Improved |
| add scale aggregation fusion (SAF) (ablation) | Direct-align · Cityscapes → Foggy Cityscapes | mAP: 38.4 -> 41.7 | Improved |
| align CNN and Transformer features together rather than aligning CNN features alone (ablation) | Direct-align · Cityscapes → Foggy Cityscapes | mAP: 38.4 -> 40.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MTTrans — MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer (ECCV 2022) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity (ICLR 2022 · similarity 0.90)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.89)
- End-to-End Object Detection with Transformers (ECCV 2020 · similarity 0.89)
- Mean Teacher DETR with Masked Feature Alignment: A Robust Domain Adaptive Detection Transformer Framework (AAAI 2024 · similarity 0.89)
- KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling (CVPR 2024 · similarity 0.88)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · 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.
