AI Paper Atlas

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

ACE: Adapting to Changing Environments for Semantic Segmentation

Zuxuan Wu, Xin Wang, Joseph E. Gonzalez, Tom Goldstein, Larry S. Davis

ICCV 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 105 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 style replay memory (100 styles per task) (ablation)ACE · Synthia Highwaymean mIoU: 61.2 -> 63.6Improved
add style replay memory (100 styles per task) (ablation)ACE · Synthia NYC-like Citymean mIoU: 46.2 -> 48.9Improved
increase stored styles from 100 to 200 per task (ablation)ACE · Synthia Highwaymean mIoU: 63.6 -> 64.0Improved
increase stored styles from 100 to 200 per task (ablation)ACE · Synthia NYC-like Citymean mIoU: 48.9 -> 49.2Improved
adapt with ACE instead of source-only modelFCN-8s-ResNet101 · Synthia Highwaymean mIoU: 60.2 -> 63.6Improved
adapt with ACE instead of source-only modelFCN-8s-ResNet101 · Synthia NYC-like Citymean mIoU: 39.3 -> 48.9Improved
adapt with ACE instead of source-only modelDeepLab V3+ · Synthia NYC-like Citymean mIoU: 28.9 -> 50.4Improved
adapt with ACE instead of source-only modelDeepLab V3+ · Synthia Highwaymean mIoU: 51.7 -> 64.5Improved
adapt with ACE instead of source-only modelResNet50-PSPNet · Synthia NYC-like Citymean mIoU: 48.4 -> 53.3Improved
transfer test images to source style (Source-Reverse) instead of adaptingsource model · Synthia NYC-like Citymean mIoU: 39.3 -> 33.1Hurt
add feature-level ADDA alignment to ACEACE · Synthia Highwaymean mIoU: 63.6 -> 64.3Improved
add feature-level ADDA alignment to ACEACE · Synthia NYC-like Citymean mIoU: 48.9 -> 49.4Improved

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