AI Paper Atlas

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

Phase Consistent Ecological Domain Adaptation

Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto

CVPR 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 127 citations (OpenAlex)

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 the scene compatibility prior (ablation)ResNet-101 segmentation model · GTA5-to-CityscapesmIoU: 44.3 -> 45.3Improved
add the scene compatibility prior (ablation)ResNet-101 segmentation model with self-supervised learning · GTA5-to-CityscapesmIoU: 47.6 -> 49.7Improved
add the scene compatibility prior (ablation)VGG-16 segmentation model · GTA5-to-CityscapesmIoU: 37.7 -> 40.9Improved
add the scene compatibility prior (ablation)VGG-16 segmentation model with self-supervised learning · GTA5-to-CityscapesmIoU: 41.3 -> 43.1Improved
add the scene compatibility prior (ablation)DRN-26 segmentation model · GTA5-to-CityscapesmIoU: 39.5 -> 41.7Improved
add phase consistency to the image transformation (ablation)UDA semantic segmentation · GTA5-to-CityscapesmIoU: 44.8 -> 45.3Improved
use output-space regularization (ablation)UDA semantic segmentation · GTA5-to-CityscapesmIoU: 45.3 -> 44.8Hurt
add the proposed domain adaptation methodResNet-101 segmentation model · GTA5-to-CityscapesmIoU: 48.5 -> 50.5Improved
add the proposed domain adaptation methodVGG-16 segmentation model · GTA5-to-CityscapesmIoU: 41.3 -> 44.6Improved
add the proposed domain adaptation methodResNet-101 segmentation model · Synthia-to-CityscapesmIoU*: 51.4 -> 53.6Improved
add the proposed domain adaptation methodVGG-16 segmentation model · Synthia-to-CityscapesmIoU*: 46.1 -> 48.7Improved

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