AI Paper Atlas

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

Learning to Optimize Domain Specific Normalization for Domain Generalization

Seonguk Seo, Yumin Suh, Dongwan Kim, Geeho Kim, Jongwoo Han, Bohyung Han

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 236 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
fine-tune BN parameters and statistics instead of fixing them (ablation)ResNet-18 baseline · PACS avgaccuracy: 80.34 -> 78.86Hurt
add domain-specific optimized IN/BN mixture (DSON)ResNet-18 baseline · PACS avgaccuracy: 78.86 -> 85.11Improved
add domain-specific optimized IN/BN mixture (DSON)ResNet-50 baseline · PACS avgaccuracy: 82.48 -> 86.64Improved
add DSONResNet-18 baseline · Office-Home avgaccuracy: 61.96 -> 62.90Improved
add DSONResNet-18 baseline · Digits avgaccuracy: 85.28 -> 87.32Improved
use DSON instead of domain-specific BN (DSBN) (ablation)ResNet-18 · PACS avgaccuracy: 77.61 -> 85.11Improved
use DSON instead of Switchable Normalization (SN) (ablation)ResNet-18 · Office-Home avgaccuracy: 58.75 -> 62.90Improved
use DSON instead of IBN (ablation)ResNet-18 · PACS avgaccuracy: 79.43 -> 85.11Improved
make IN/BN mixture weights domain-specific rather than shared (ablation)DSON · PACS multi-source DG avgaccuracy: 82.82 -> 85.11Improved
use DSON under label noise 0.5ResNet-18 · PACS label noise 0.5 avgaccuracy: 71.59 -> 81.59Improved
add DSON to multi-source domain adaptation baselineShu et al. baseline · PACS multi-source DA avgaccuracy: 83.30 -> 90.38Improved
use DSON instead of DSBN in multi-source domain adaptation (ablation)Shu et al. baseline · PACS multi-source DA avgaccuracy: 87.32 -> 90.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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