AI Paper Atlas

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

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 34 citations (OpenAlex)

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 changedWhereMeasuredEffect
add PITSWDA · Cityscapes -> KITTI detectioncar AP: 72.42 -> 75.77Improved
add PITSCL · Cityscapes -> KITTI detectioncar AP: 75.28 -> 77.11Improved
add PITGPA · Cityscapes -> KITTI detectioncar AP: 69.24 -> 74.51Improved
add PITGPA · Virtual KITTI -> KITTI detectioncar AP: 65.36 -> 70.71Improved
add PITSWDA · KITTI subset -> Cityscapes detectioncar AP: 39.67 -> 41.68Improved
add PITGPA · Virtual KITTI subset -> Cityscapes detectioncar AP: 44.56 -> 45.56Improved
add PITSelf-Ensembling · Cityscapes -> KITTI segmentationmIoU: 59.54 -> 61.00Improved
add PITDACS · Virtual KITTI -> KITTI segmentationmIoU: 55.51 -> 56.57Improved
add PIT on top of data augmentation (ablation)SWDA + Aug · Cityscapes -> KITTI detectioncar AP: 74.74 -> 76.93Improved
add data augmentation to PIT (ablation)SWDA + PIT · Cityscapes -> KITTI detectioncar AP: 75.77 -> 76.93Improved
add PIT to source-only detector tested with wider FoV (ablation)Faster R-CNN · KITTI source-only, FoVx 90car AP: 84.92 -> 86.43Improved
use loss re-weighting instead of reverse PIT (ablation)Self-Ensembling + PIT · Cityscapes -> KITTI segmentationmIoU: 60.62 -> 61.00No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy