AI Paper Atlas

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

Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters

Mateusz Michalkiewicz, Masoud Faraki, Xiang Yu, Manmohan Chandraker, Mahsa Baktashmotlagh

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 13 citations (OpenAlex)

This paper tried a common change: Add dropout

add GSNR-guided dropout to SSAN · OCIM average HTER · HTER: 13.21 -> 11.02 Improved

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
mask by GSNR instead of random Bernoulli in DropBlock (ablation)DropBlock · PACSaverage accuracy: 79.2 -> 84.43Improved
mask by GSNR instead of gradient magnitude in DropBlock (ablation)DropBlock · PACSaverage accuracy: 83.15 -> 84.43Improved
mask by GSNR instead of gradient magnitude in SpatialDropout (ablation)SpatialDropout · PACSaverage accuracy: 83.22 -> 83.31No clear effect
mask by GSNR instead of gradient magnitude in RSC (ablation)RSC · PACSaverage accuracy: 83.90 -> 84.38Improved
meta-learn dropout ratios instead of grid search (ablation)DB + GSNR · PACSaverage accuracy: 85.37 -> 85.84Improved
learn dropout ratios by meta-learning instead of fixed ratio (ablation)DB + GSNR · PACSaverage accuracy: 84.43 -> 85.84Improved
add CutOut, MixUp, CutMix or Manifold Mixup to baseline (ablation)ResNet18 baseline · PACSaverage accuracy: 79.5 -> 76.8 (CutMix)Hurt
add GSNR-guided dropout to SSANSSAN · OCIM average HTERHTER: 13.21 -> 11.02Improved
add GSNR-guided dropout to EPCREPCR · OCIM average HTERHTER: 11.36 -> 10.47Improved
GSNR dropout vs RSC on Office-HomeRSC · Office-Homeaverage accuracy: 63.12 -> 65.28Improved
add GSNR-guided dropout to SSAN on the O&C&I to M protocolSSAN · OCIM O&C&I to M AUCAUC: 97.50 -> 95.50Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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