AI Paper Atlas

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

Curriculum Manager for Source Selection in Multi-Source Domain Adaptation

Luyu Yang, Yogesh Balaji, Ser-Nam Lim, Abhinav Shrivastava

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 119 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 the adversarial curriculum manager for source sample weightingDANN (combined sources) · DomainNet averageaccuracy (%): 43.0 -> 46.5Improved
add the adversarial curriculum manager for source sample weightingDANN (combined sources) · DomainNet quickdraw targetaccuracy (%): 7.7 -> 16.0Improved
use CMSS weighting instead of IWAN discriminator-based sample weightsIWAN · DomainNet averageaccuracy (%): 43.1 -> 46.5Improved
use CMSS instead of M3SDAM3SDA · Digits averageaccuracy (%): 87.6 -> 90.8Improved
use CMSS instead of M3SDAM3SDA · PACS averageaccuracy (%): 88.3 -> 89.5Improved
use CMSS instead of M3SDAM3SDA · PACS sketch targetaccuracy (%): 76.7 -> 82.0Improved
use CMSS instead of M3SDAM3SDA · Office-Caltech10 averageaccuracy (%): 96.4 -> 97.2Improved
use CMSS instead of MDANMDAN · Digits to MNIST-M targetaccuracy (%): 75.7 -> 75.3No clear effect
use CMSS instead of WBNWBN · PACS photo/art targetsaccuracy (%): 89.9 -> 88.6Mixed
train DANN on combined sources versus Source OnlySource Only · DomainNet quickdraw targetaccuracy (%): 13.0 -> 7.7Hurt

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