AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation

Miaoyu Li, Yachao Zhang, Xu Ma, Yanyun Qu, Yun Fu

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 21 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 BEV-based area-to-area fusion (BAF) to baseline (ablation)Baseline · A,N->S (SemanticKITTI)mIoU Avg: 44.7 -> 52.9Improved
add BEV-driven domain contrastive learning (BDCL) to baseline (ablation)Baseline · A,N->S (SemanticKITTI)mIoU Avg: 44.7 -> 49.4Improved
combine BAF and BDCL (ablation)Baseline · A,S->N (nuScenes)mIoU Avg: 53.9 -> 59.0Improved
add BEV transformation (use BEV areas rather than point-level concatenation) (ablation)BEV-DG · A,N->S (SemanticKITTI)mIoU Avg: 38.7 -> 60.2Improved
add fusion of 2D and 3D BEV feature maps (ablation)BEV-DG · A,N->S (SemanticKITTI)mIoU Avg: 45.3 -> 60.2Improved
add Density-maintained Vector Modeling (DVM) (ablation)BEV-DG · A,N->S (SemanticKITTI)mIoU Avg: 50.0 -> 60.2Improved
add Density Transfer (DT) for positive pairs (ablation)BEV-DG · A,N->S (SemanticKITTI)mIoU Avg: 49.1 -> 60.2Improved
area-to-area fusion instead of point-to-point cross-modal learning under projection misalignmentBAF / BEV-DG vs xMUDA, Dual-Cross · A,S->N (nuScenes)mIoU AvgImproved
vary BEV area size w from 0.05m to 1m (ablation)BEV-DG · A,S->N (nuScenes)mIoUMixed
vary contrastive loss weight from 0.001 to 0.1 (ablation)BEV-DG · A,S->N (nuScenes)mIoUNo clear effect
BEV-DG versus best prior method on 3D mIoU in A,N->SBEV-DG · A,N->S (SemanticKITTI)mIoU 3D: 56.5 -> 54.7Hurt

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