AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception

Kai Jiang, Jiaxing Huang, Weiying Xie, Jie Lei, Yunsong Li, Ling Shao, Shijian Lu

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose · 4 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 query-based adversarial learning on image-view features (ablation)PETR · Daytime->NighttimemAP: 15.93 -> 16.45Improved
add BEV QAL alongside image-view QAL (ablation)DA-BEV · Daytime->NighttimemAP: 16.45 -> 16.96Improved
add co-regularization between image-view and BEV QAL (ablation)DA-BEV · Daytime->NighttimemAP: 16.96 -> 17.80Improved
add image-view query-based self-training (ablation)DA-BEV · Daytime->NighttimemAP: 17.80 -> 18.53Improved
add BEV query-based self-training (ablation)DA-BEV · Daytime->NighttimemAP: 18.53 -> 19.39Improved
add co-regularization of QST between image-view and BEV (ablation)DA-BEV · Daytime->NighttimemAP: 19.39 -> 20.27Improved
pseudo-label ratio 10% instead of 20% (ablation)QST · Daytime->NighttimemAP: 20.27 -> 18.24Hurt
vary pseudo-label ratio between 15% and 30% (ablation)QST · Daytime->NighttimemAP: 19.83 -> 19.57No clear effect
EMA gamma 0.9 instead of 0.999 (ablation)QST · Daytime->NighttimemAP: 20.27 -> 17.20Hurt
apply DA-BEV on top of BEVFormerBEVFormer · Daytime->NighttimemAP: 15.73 -> 19.15Improved
apply DA-BEV on ResNet-50-C5 backbonePETR · Daytime->NighttimemAP: 10.63 -> 13.03Improved
apply DA-BEV to 3D scene segmentationPETR · Daytime->Nighttime segmentationmIoU: 28.01 -> 35.59Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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