AI Paper Atlas

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

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

Vitor Guizilini, Jie Li, Rareș Ambruș, Adrien Gaidon

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 38 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 geometric self-supervision (photometric loss on target videos) to pseudo-label training (ablation)GUDA · Cityscapes SYNTHIAmIoU: 46.8 -> 51.0Improved
add geometric self-supervision to virtual supervision (ablation)GUDA · Cityscapes SYNTHIAmIoU: 33.8 -> 44.5Improved
add surface normal supervision on virtual samples (ablation)GUDA · Cityscapes SYNTHIAmIoU: 43.4 -> 44.5Improved
use 30 context frames instead of 2 (ablation)GUDA · Cityscapes SYNTHIAmIoU: 43.8 -> 44.5Improved
train DADA with 30 frames instead of 1 (ablation)DADA · Cityscapes SYNTHIAmIoU: 42.6 -> 42.4No clear effect
train at multiple resolutions instead of full resolution only (ablation)GUDA · Cityscapes SYNTHIAmIoU: 44.3 -> 44.5Improved
add domain adversarial DANN loss (ablation)GUDA · Cityscapes SYNTHIAmIoU: 44.5 -> 44.8Improved
add USAMR pseudo-label supervision (ablation)GUDA · Cityscapes SYNTHIAmIoU: 44.5 -> 51.0Improved
raise pseudo-label loss weight beyond 0.01 (ablation)GUDA+PL · Cityscapes SYNTHIAmIoUHurt
add partially-supervised photometric loss (ablation)GUDA (R18) · KITTI depthAbs.Rel: 0.114 -> 0.109Improved
add partially-supervised photometric loss (ablation)GUDA (R18) · DDAD depthAbs.Rel: 0.166 -> 0.158Improved
replace fine-tuning with GUDA trainingResNet18 depth network · KITTI depthAbs.Rel: 0.114 -> 0.109Improved

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