AI Paper Atlas

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

Unsupervised Domain Adaptation for Semantic Segmentation using Depth Distribution

Quanliang Wu, Huajun Liu

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 1 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 density estimation branch to segmentation+depth model (ablation)Multi-task UDA model · SYNTHIA->Cityscapes (16 classes)mIoU: 41.7 -> 44.8Improved
Add confidence-based self-training (ablation)Model M2 · SYNTHIA->Cityscapes (16 classes)mIoU: 44.8 -> 47.6Improved
Add spatial prior pseudo-label refinement to self-training (ablation)Model M3 · SYNTHIA->Cityscapes (16 classes)mIoU: 47.6 -> 48.2Improved
Add branch balance loss with online density map on target domain (ablation)Proposed model without self-training · SYNTHIA->Cityscapes (16 classes)mIoU: 44.1 -> 44.8Improved
Use ground-truth depth rather than predicted depth to build source density map (ablation)Proposed model without self-training · SYNTHIA->Cityscapes (16 classes)mIoU: 43.4 -> 44.8Improved
Fuse all three branches' results instead of density+segmentation only (ablation)Proposed model without self-training · SYNTHIA->Cityscapes (16 classes)mIoU: 44.8 -> 37.8Hurt
Use DADA-style depth+segmentation fusion instead of density+segmentation fusion (ablation)Proposed model without self-training · SYNTHIA->Cityscapes (16 classes)mIoU: 44.8 -> 43.7Hurt
Add density estimation branch to improve depth (ablation)M1 vs M2 · Cityscapes depth|Rel|: 0.7 -> 0.5Improved
Add density estimation branch to improve depth accuracy (ablation)M1 vs M2 · Cityscapes depthdelta1: 0.21 -> 0.26Improved
Raise auxiliary task weights to 1e-1 or lower them to 1e-3 (ablation)Proposed model · SYNTHIA->Cityscapes (16 classes)mIoUHurt
Vary auxiliary task weights within the 1e-2 level (ablation)Proposed model · SYNTHIA->Cityscapes (16 classes)mIoUNo clear effect
Use our model instead of CTRLProposed model · SYNTHIA->Mapillary (7 classes) 320x640mIoU: 62.5 -> 60.3Hurt

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