AI Paper Atlas

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

Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

Christos Sakaridis, Dengxin Dai, Luc Van Gool

TPAMI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 211 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 twilight data to nighttime adaptation (no curriculum) (ablation)single-stage adaptation · Dark Zurich-testmIoU: 33.6 -> 34.0No clear effect
add two-stage curriculum with twilight (ablation)adaptation w/ twilight · Dark Zurich-testmIoU: 34.0 -> 38.2Improved
add guided refinement with cross bilateral filtering (ablation)MGCDA w/o guided refinement · Dark Zurich-testmIoU: 38.2 -> 40.3Improved
use depth-based warping instead of cross bilateral filtering (ablation)MGCDA · Dark Zurich-testmIoU: 40.3 -> 42.5Improved
train CycleGAN on full 360x720 images instead of 256x256 crops (ablation)synthetic adaptation · Dark Zurich-testmIoU: 37.1 -> 40.2Improved
add map guidance at test time (ablation)MGCDA · Dark Zurich-testmIoU: 42.5 -> 44.1Improved
add map guidance at test time (ablation)DMAda · Dark Zurich-testmIoU: 32.1 -> 34.8Improved
preprocess nighttime images with CycleGAN before daytime model (ablation)RefineNet · Dark Zurich-testmIoU: 28.5 -> 7.2Hurt
preprocess with CLAHE (ablation)RefineNet · Dark Zurich-testmIoU: 28.5 -> 23.0Hurt
preprocess with ZeroDCE (ablation)RefineNet · Dark Zurich-testmIoU: 28.5 -> 17.9Hurt
enhance synthetic nighttime images with ZeroDCE during adaptation (ablation)RefineNet adaptation · Dark Zurich-testmIoU: 40.2 -> 38.4Hurt
use MGCDA instead of GCMAadaptation pipeline · Nighttime DrivingmIoU: 45.6 -> 49.4Improved

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