AI Paper Atlas

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

Learning Across Tasks and Domains

Pierluigi Zama Ramirez, Alessio Tonioni, Samuele Salti, Luigi Di Stefano

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 36 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 a single task-1 network shared across both domains (ablation)AT/DT · Synthia->Cityscapes, depth-to-semantics (target)mIoU: 6.42 -> 23.24 (+16.82)Improved
add a single shared task-1 network (ablation)AT/DT · Synthia->Cityscapes (target)accuracy: 29.36 -> 64.03 (+34.67)Improved
add a single shared task-1 network (ablation)AT/DT · Synthia (source domain A)mIoU: 61.73 -> 65.41Improved
add batch normalization to the task networks (ablation)AT/DT · Synthia->Cityscapes, target domainaccuracy: 58.29 -> 64.03 (+5.74)Improved
add batch normalization to the task networks (ablation)AT/DT · Synthia->Cityscapes, target domainmIoU: 22.75 -> 23.24 (+0.49)Improved
add batch normalization to the task networks (ablation)AT/DT · Synthia (source domain A)mIoU: 72.48 -> 65.41Hurt
transfer features at deeper layers of the network (ablation)AT/DT · Synthia->Cityscapes, depth-to-semanticsAcc and mIoUImproved
add AT/DT cross-task transfer over the baselinetask-2 network trained on A · Synthia->Carla, depth-to-semanticsmIoU: 34.12 -> 43.14Improved
add AT/DT cross-task transfer over the baselinetask-2 network trained on A · Synthia->Cityscapes, depth-to-semanticsmIoU: 7.72 -> 23.24Improved
add AT/DT cross-task transfer over the baselinetask-2 network trained on A · Carla->Cityscapes, semantics-to-depthAbs Rel: 0.667 -> 0.394Improved
add AT/DT cross-task transfer over the baselinetask-2 network trained on A · Carla->Kitti, semantics-to-depthAbs Rel: 0.500 -> 0.439Improved
add CycleGAN pixel-level domain adaptationbaseline · Carla->Cityscapes, depth-to-semanticsmIoU: 37.88 -> 42.33Improved

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