AI Paper Atlas

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

MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation

Munan Ning, Donghuan Lu, Yujia Xie, Dongdong Chen, Dong Wei, Yefeng Zheng, Yonghong Tian, Shuicheng Yan, Li Yuan

TPAMI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 16 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 target samples (5%) with cross-entropy (ablation)MADAv2 baseline · GTA5 to CityscapesmIoU: 42.5 -> 65.1Improved
add consistency loss and self-training (ablation)MADAv2 · GTA5 to CityscapesmIoU: 65.1 -> 68.5Improved
add OHEM loss (ablation)MADAv2 · GTA5 to CityscapesmIoU: 68.5 -> 69.5Improved
add ACM and ACP augmentation (ablation)MADAv2 · GTA5 to CityscapesmIoU: 69.5 -> 70.8Improved
add soft-anchor alignment loss (ablation)MADAv2 · GTA5 to CityscapesmIoU: 70.8 -> 71.4Improved
add active samples (ablation)MADAv2 baseline · SYNTHIA to CityscapesmIoU: 42.9 -> 65.2Improved
add soft-anchor alignment loss (ablation)MADAv2 · SYNTHIA to CityscapesmIoU: 71.1 -> 71.8Improved
select samples with Dual_Domain_Distance instead of single-centroid prototype distance (ablation)MADAv2 selection · GTA5 to CityscapesmIoU: 63.1 -> 65.1Improved
select samples with Dual_Domain_Distance instead of random (ablation)MADAv2 selection · GTA5 to CityscapesmIoU: 61.1 -> 65.1Improved
use MADAv2 sample selection instead of MADA selection with MADAv2 semi-supervision (ablation)MADAv2 · GTA5 to CityscapesmIoU: 70.5 -> 71.4Improved
use MADAv2 semi-supervision instead of MADA with MADA selection (ablation)MADA selection · GTA5 to CityscapesmIoU: 66.9 -> 70.5Improved
use only target anchor distance and only target data (drop source information) (ablation)MADAv2 · GTA5 to CityscapesmIoU: 71.4 -> 67.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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