AI Paper Atlas

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

Efficient Active Domain Adaptation for Semantic Segmentation by Selecting Information-rich Superpixels

Yuan Gao, Zilei Wang, Yixin Zhang, Bohai Tu

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 0 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 ASAL fusion with low-uncertainty superpixel fusion (ablation)superpixel active domain adaptation · GTA5->CityscapesmIoU upper bound: 69.11% -> 72.58%Improved
fuse low-uncertainty superpixels (873 clicks) versus labeling all original superpixels (4,985) (ablation)DeepLabv2 · GTA5->CityscapesmIoU: 73.1 -> 72.6No clear effect
use two-stage acquisition (A1 large merged superpixels then A2) instead of single-stage DS (ablation)DeepLabv2 at 40 clicks · GTA5->CityscapesmIoU: 58.5 -> 68.7Improved
use two-stage acquisition instead of ASAL (ablation)DeepLabv2 at 40 clicks · GTA5->CityscapesmIoU: 57.0 -> 68.7Improved
use domain-difference selection in phase 2 versus other selection algorithms (ablation)A2 · GTA5->CityscapesmIoU: +0.41% to +0.65% over second placeImproved
add cross-domain mixing (ablation)baseline supervised training · GTA5->Cityscapes (40 clicks)mIoU: 63.9 -> 67.4Improved
add pseudo labels on target domain (ablation)M(1) · GTA5->Cityscapes (40 clicks)mIoU: 67.4 -> 68.0Improved
add consistency regularization on domain-mix samples (ablation)M(2) · GTA5->Cityscapes (40 clicks)mIoU: 68.0 -> 68.7Improved
apply training techniques to RIPU (ablation)RIPU (11,535 clicks) · GTA5->CityscapesmIoU: 62.8 -> 71.9Improved
use superpixel-level labeling with 640 clicks versus pixel-level 26,215 clicksDeepLabv3+ · GTA5->CityscapesmIoU: 71.3 -> 72.9Improved

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