AI Paper Atlas

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

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

Jintao Guo, Lei Qi, Yinghuan Shi

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 72 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
apply DomainDrop to all layers (ablation)ResNet-18 baseline · PACSaverage accuracy (%): 81.00 -> 85.06Improved
add DomainDrop to OfficeHome ResNet-18 baseline (ablation)ResNet-18 baseline · OfficeHomeaverage accuracy (%): 63.59 -> 65.30Improved
add layer-wise training scheme (ablation)DomainDrop · PACSaverage accuracy (%): 85.06 -> 85.94Improved
add dual consistency loss (ablation)DomainDrop · PACSaverage accuracy (%): 85.06 -> 85.74Improved
combine layer-wise training and consistency loss with DomainDrop (ablation)DomainDrop · PACSaverage accuracy (%): 85.94 -> 86.66Improved
set dropout ratio to 0.33 (ablation)DomainDrop · PACSaverage accuracy (%)No clear effect
apply DomainDrop with probability at least 0.7 (ablation)DomainDrop · PACSaverage accuracy (%)No clear effect
add DomainDrop to FACTFACT · PACS (ResNet-18)average accuracy (%): 84.61 -> 87.24Improved
add DomainDrop to RandAugRandAug · PACS (ResNet-18)average accuracy (%): 83.63 -> 86.69Improved
add DomainDrop to GFNetGFNet · PACSaverage accuracy (%): 87.76 -> 91.02Improved
apply DomainDrop to reduce domain divergenceResNet-18 · PACSsource-target divergence (x10): 7.25 -> 4.09Improved
use traditional dropout (Cutout, C-Drop) on source domainsResNet-18 · PACSaverage accuracy (%): 81.00 -> 80.60 (Cutout), 81.11 (C-Drop)No clear effect

Later papers that compared with this method

1 later accepted paper reports DomainDrop as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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