AI Paper Atlas

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

Multi-Anchor Active Domain Adaptation for Semantic Segmentation

Munan Ning, Donghuan Lu, Dong Wei, Cheng Bian, Chenglang Yuan, Shuang Yu, Kai Ma, Yefeng Zheng

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 64 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 active samples with cross-entropy loss (ablation)adversarial DA baseline · GTA5->CityscapesmIoU: 42.5 -> 61.6Improved
add active samples with cross-entropy loss (ablation)adversarial DA baseline · SYNTHIA->CityscapesmIoU: 42.9 -> 65.0Improved
add multi-anchor soft alignment loss (ablation)MADA · GTA5->CityscapesmIoU: 61.6 -> 63.2Improved
add multi-anchor soft alignment loss (ablation)MADA · SYNTHIA->CityscapesmIoU: 65.0 -> 66.6Improved
update target anchors with EMA (ablation)MADA · GTA5->CityscapesmIoU: 63.2 -> 63.8Improved
update target anchors with EMA (ablation)MADA · SYNTHIA->CityscapesmIoU: 66.6 -> 67.6Improved
add pseudo label loss on unlabeled target (ablation)MADA · GTA5->CityscapesmIoU: 63.8 -> 64.9Improved
add pseudo label loss on unlabeled target (ablation)MADA · SYNTHIA->CityscapesmIoU: 67.6 -> 68.1Improved
multi-anchor selection instead of AADA selectionactive learning · GTA5->CityscapesmIoU: 59.3 -> 61.6Improved
multi-anchor selection instead of random selectionactive learning · GTA5->CityscapesmIoU: 56.7 -> 61.6Improved
increase active sample fraction from 1% to 20% (ablation)MADA · GTA5->CityscapesmIoU: 56.7 -> 64.1Improved
use K-means instead of spectral clustering (ablation)MADA · GTA5->CityscapesmIoU: 61.02 -> 61.58Improved

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