AI Paper Atlas

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

Domain Adaptive Semantic Segmentation With Self-Supervised Depth Estimation

Qin Wang, Dengxin Dai, Lukas Hoyer, Luc Van Gool, Olga Fink

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 149 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 self-supervised depth auxiliary task naively (ablation)DACS · SYNTHIA-to-CityscapesmIoU: 48.3 -> 49.6Improved
add task feature correlation module to depth auxiliary (ablation)SimpleAux · SYNTHIA-to-CityscapesmIoU: 49.6 -> 54.2Improved
add task feature correlation module to depth auxiliary (ablation)SimpleAux · SYNTHIA-to-Cityscapes (13 classes)mIoU*: 55.9 -> 62.4Improved
add correlation learning modules (ablation)CorDA without correlation modules · SYNTHIA-to-CityscapesmIoU: 51.7 -> 54.2Improved
add pseudo-label refinement with adaptation difficulty (ablation)CorDA (F) · SYNTHIA-to-CityscapesmIoU: 54.2 -> 55.0Improved
add pseudo-label refinement with adaptation difficulty (ablation)CorDA (F) · SYNTHIA-to-Cityscapes (13 classes)mIoU*: 62.4 -> 62.8Improved
use stereo depth instead of Monodepth2 monocular depth for Cityscapes (ablation)CorDA · SYNTHIA-to-CityscapesmIoU: 54.5 -> 55.0Improved
use ImageNet+COCO weights instead of ImageNet-only (ablation)CorDA · SYNTHIA-to-CityscapesmIoU: 54.6 -> 55.0No clear effect
use ImageNet+COCO weights instead of ImageNet-only (ablation)CorDA · GTA5-to-CityscapesmIoU: 56.4 -> 56.6No clear effect
add CorDA to DACS frameworkDACS · SYNTHIA-to-CityscapesmIoU: 48.3 -> 55.0Improved
add CorDA to DACS frameworkDACS · GTA5-to-CityscapesmIoU: 52.1 -> 56.6Improved
use feature-correlation learning instead of adversarial depth useDADA · SYNTHIA-to-CityscapesmIoU: 42.6 -> 55.0Improved

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