AI Paper Atlas

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

Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool

CVPR 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 62 citations (OpenAlex)

Check 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
Use CTRL to align a joint space of task-specific and cross-task featuresSemantic and depth UDA model · SYNTHIA → Cityscapes (7 classes, full resolution, EP2)mIoU: 69.2 to 70.7Improved
Use CTRL to align a joint space of task-specific and cross-task featuresSemantic and depth UDA model · SYNTHIA → Mapillary (7 classes, low resolution, EP3)mIoU: +2.9%Improved
Add depth supervision to semantic supervision (ablation)C1 semantic-only model · SYNTHIA → Cityscapes validationmIoU: 30.7 -> 35.2Improved
Add SRH supervision to semantic and depth supervision in supervised-only training (ablation)C2 · SYNTHIA → Cityscapes validationmIoU: 35.2 -> 33.1Hurt
Add depth-space adversarial alignment to semantic-space alignment (ablation)C5 · SYNTHIA → Cityscapes validationmIoU: 40.8 -> 40.2Hurt
Add iterative self-learning to the CTRL configuration (ablation)C8 · SYNTHIA → Cityscapes validationmIoU: 42.1 -> 44.9Improved
Add SRH to iterative self-learning with semantic and depth supervision and adversarial alignment (ablation)C10 · SYNTHIA → Cityscapes validationmIoU: 42.8 -> 44.9Improved
Use CTRL and SRH rather than DADA's approachMonocular depth estimation model · Cityscapes validation (trained on SYNTHIA → Cityscapes, EP1)|Rel|: 0.6 to 0.3Improved
Use the proposed method rather than DADASemantic UDA model · Virtual KITTI → KITTImIoU: 53.0 to 54.6Improved

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