AI Paper Atlas

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

Information-Theoretic Regularization for Multi-Source Domain Adaptation

Geon Yeong Park, Sang Wan Lee

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 42 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 M3SDA-beta with MIAN (single unified domain discriminator)multi-source DA · Digits-Five avgaccuracy: 87.65 -> 92.03Improved
replace M3SDA-beta with MIANmulti-source DA · Digits-Five MNIST-Maccuracy: 72.82 -> 84.36Improved
replace M3SDA-beta with MIANmulti-source DA · Office-31 avgaccuracy: 89.45 -> 90.87Improved
replace M3SDA with MIANmulti-source DA · Office-Home avgaccuracy: 71.39 -> 73.12Improved
add decaying batch spectral penalization (MIAN-gamma) to MIANMIAN · Office-31 avgaccuracy: 90.87 -> 91.26Improved
add decaying batch spectral penalization (MIAN-gamma) to MIANMIAN · Office-Home avgaccuracy: 73.12 -> 74.11Improved
use one unified domain discriminator instead of multiple discriminators (Multi D) (ablation)MIAN · MNIST-M and SVHN targetsaccuracyImproved
use one unified domain discriminator instead of multiple discriminators (ablation)MIAN · MNIST-M and SVHN targetsgradient varianceImproved
use binary cross entropy instead of multi-class cross entropy for the discriminator objective (ablation)MIAN · Digits-FiveaccuracyImproved
use binary cross entropy instead of multi-class cross entropy for the discriminator objective (ablation)MIAN · Digits-Fiveproxy A-distance / mutual informationImproved
add decaying spectral penalization and annealed information regularization (ablation)MIAN · Office-31 (DSLR to Amazon)accuracyImproved
use constant spectral penalization (BSP) instead of decaying (ablation)MIAN · Office-31 low-shift targets (Webcam, DSLR)accuracyHurt

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