AI Paper Atlas

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

Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation

Jinyu Yang, Weizhi An, Sheng Wang, Xinliang Zhu, Chaochao Yan, Junzhou Huang

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 108 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
replace source-to-target with target-to-source translation (ablation)DeepLab-ResNet101 baseline · GTA5 to CityscapesmIoU: 48.5 -> 49.1Improved
replace source-to-target with target-to-source translation (ablation)FCN-VGG16 baseline · GTA5 to CityscapesmIoU: 41.3 -> 42.3Improved
replace source-to-target with target-to-source translation (ablation)DeepLab-ResNet101 baseline · SYNTHIA to CityscapesmIoU: 51.4 -> 52.0Improved
replace source-to-target with target-to-source translation (ablation)FCN-VGG16 baseline · SYNTHIA to CityscapesmIoU: 39.0 -> 40.1Improved
add label-driven reconstruction network (ablation)target-to-source translation, ResNet101 · GTA5 to CityscapesmIoU: 49.1 -> 49.5Improved
add label-driven reconstruction network (ablation)target-to-source translation, VGG16 · GTA5 to CityscapesmIoU: 42.3 -> 43.6Improved
add label-driven reconstruction network (ablation)target-to-source translation, ResNet101 · SYNTHIA to CityscapesmIoU: 52.0 -> 53.1Improved
add label-driven reconstruction network (ablation)target-to-source translation, VGG16 · SYNTHIA to CityscapesmIoU: 40.1 -> 41.1Improved
reconstruct from label space instead of feature space (ablation)reconstruction network, VGG16 · GTA5 to CityscapesmIoU: 41.48 -> 43.6Improved
reconstruct from label space instead of feature space (ablation)reconstruction network, VGG16 · SYNTHIA to CityscapesmIoU: 40.13 -> 41.1Improved
set Boltzmann temperature tau to 0.001 instead of 1 (ablation)reconstruction from label space, VGG16 · GTA5 to CityscapesmIoU: 41.5 -> 43.6Improved
add VGG perceptual loss to reconstruction loss (ablation)reconstruction loss, VGG16 · GTA5 to CityscapesmIoU: 41.53 -> 42.82Improved

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