AI Paper Atlas

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

Union-Set Multi-source Model Adaptation for Semantic Segmentation

Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 5 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 cross-model consistency to self-training (ablation)ST · Cityscapes (non-overlapping, S+G)mIoU: 42.3 -> 43.2Improved
add adversarial learning on top of cross-model consistency (ablation)ST+CMC · Cityscapes (non-overlapping, S+G)mIoU: 43.2 -> 44.0Improved
add maximum squares loss (ablation)ST+CMC+ADV · Cityscapes (non-overlapping, S+G)mIoU: 44.0 -> 45.8Improved
add model integration by distillation (Stage II) (ablation)Stage I of PM · Cityscapes (non-overlapping, S+G)mIoU: 45.8 -> 46.6Improved
add cross-model consistency to self-training (ablation)ST · Cityscapes (partly-overlapping, S+G)mIoU: 44.2 -> 46.0Improved
add maximum squares loss (ablation)ST+CMC+ADV · Cityscapes (partly-overlapping, S+G)mIoU: 46.6 -> 47.4Improved
add model integration (ablation)Stage I of PM · Cityscapes (partly-overlapping, S+G)mIoU: 47.4 -> 48.3Improved
add model-invariant feature learning to common classes of S+T (ablation)ST · Cityscapes (partly-overlapping, S+T, common classes)mIoU: 49.6 -> 49.8No clear effect
add maximum squares loss (ablation)ST+CMC+ADV · Cityscapes (fully-overlapping, S+G)mIoU: 50.9 -> 51.0No clear effect
add model integration (ablation)Stage I of PM · Cityscapes (fully-overlapping, S+G)mIoU: 51.0 -> 51.7Improved
use proposed method instead of weighted-ensemble MSMAMSMA · Cityscapes (non-overlapping, S+G)mIoU: 30.2 -> 46.6Improved
use proposed method (Stage I only) instead of SSMA/UDAStage I of PM · Cityscapes (partly-overlapping, S+G)mIoU: 47.4 -> 47.9Hurt

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