Research map / Detection and segmentation / Open-set and few-shot detection
PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
Qiqi Gu, Qianyu Zhou, Minghao Xu, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
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 PIT | SWDA · Cityscapes -> KITTI detection | car AP: 72.42 -> 75.77 | Improved |
| add PIT | SCL · Cityscapes -> KITTI detection | car AP: 75.28 -> 77.11 | Improved |
| add PIT | GPA · Cityscapes -> KITTI detection | car AP: 69.24 -> 74.51 | Improved |
| add PIT | GPA · Virtual KITTI -> KITTI detection | car AP: 65.36 -> 70.71 | Improved |
| add PIT | SWDA · KITTI subset -> Cityscapes detection | car AP: 39.67 -> 41.68 | Improved |
| add PIT | GPA · Virtual KITTI subset -> Cityscapes detection | car AP: 44.56 -> 45.56 | Improved |
| add PIT | Self-Ensembling · Cityscapes -> KITTI segmentation | mIoU: 59.54 -> 61.00 | Improved |
| add PIT | DACS · Virtual KITTI -> KITTI segmentation | mIoU: 55.51 -> 56.57 | Improved |
| add PIT on top of data augmentation (ablation) | SWDA + Aug · Cityscapes -> KITTI detection | car AP: 74.74 -> 76.93 | Improved |
| add data augmentation to PIT (ablation) | SWDA + PIT · Cityscapes -> KITTI detection | car AP: 75.77 -> 76.93 | Improved |
| add PIT to source-only detector tested with wider FoV (ablation) | Faster R-CNN · KITTI source-only, FoVx 90 | car AP: 84.92 -> 86.43 | Improved |
| use loss re-weighting instead of reverse PIT (ablation) | Self-Ensembling + PIT · Cityscapes -> KITTI segmentation | mIoU: 60.62 -> 61.00 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CutMix — CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features (ICCV 2019) · better on 1 of 1 shared result
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 1 of 1 shared result
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
- Adapting Object Detectors via Selective Cross-Domain Alignment (CVPR 2019 · similarity 0.87)
- OA-FSUI2IT: A Novel Few-Shot Cross Domain Object Detection Framework with Object-Aware Few-Shot Unsupervised Image-to-Image Translation (AAAI 2022 · similarity 0.87)
- Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection (CVPR 2023 · similarity 0.87)
- Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector (ECCV 2024 · similarity 0.87)
- Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection (NeurIPS 2025 · similarity 0.87)
- Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection (NeurIPS 2024 · similarity 0.85)
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.
