AI Paper Atlas

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

ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation

Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, Yun Fu

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 62 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 ECACL-P framework to MMEMME ResNet-34 · VisDA2017 1-shotMCA: 68.4 -> 81.1Improved
add ECACL-P framework to MMEMME ResNet-34 · VisDA2017 3-shotMCA: 71.2 -> 83.3Improved
add ECACL-P as plug-and-play on HAFNHAFN ResNet-101 · VisDA2017 1-shotMCA: 77.0 -> 83.9Improved
add ECACL-P as plug-and-play on SAFNSAFN ResNet-101 · VisDA2017 3-shotMCA: 79.2 -> 84.5Improved
add ECACL-P to MMEMME ResNet-34 · Office-Home 1-shot meanaccuracy: 49.2 -> 52.4Improved
add ECACL-P to MMEMME ResNet-34 · Office-Home 3-shot meanaccuracy: 55.2 -> 59.1Improved
add categorical (prototypical) alignment (ablation)MME · DomainNet Real to Sketch 3-shotaccuracy: 37.9 -> 39.2Improved
add strong augmentation (ablation)MME · DomainNet Real to Sketch 3-shotaccuracy: 37.9 -> 39.3Improved
add consistency alignment (ablation)MME · DomainNet Real to Sketch 3-shotaccuracy: 37.9 -> 43.5Improved
add consistency alignment to CA+SA (ablation)ECACL-P · DomainNet Real to Sketch 3-shotaccuracy: 42.2 -> 48.4Improved
add strong augmentation to CA+CONA (ablation)ECACL-P · DomainNet Real to Sketch 3-shotaccuracy: 45.2 -> 48.4Improved
use prototype-based instead of triplet-based categorical alignment (ResNet-34) (ablation)ECACL · DomainNetaccuracyImproved

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