AI Paper Atlas

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

GeT: Generative Target Structure Debiasing for Domain Adaptation

Can Zhang, Gim Hee Lee

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 4 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 nearest-centroid classifier with online generative (GMM) classifier for pseudo labels (ablation)GeT · VisDA-2017average accuracy (%): 80.3 -> 81.4Improved
add embedding-level structure similarity regularization (L_KL^f) (ablation)GeT · VisDA-2017average accuracy (%): 80.6 -> 83.4Improved
add mixed soft labels from generative classifier and auxiliary distribution (ablation)GeT · VisDA-2017average accuracy (%): 82.0 -> 83.4Improved
add structure similarity regularization and mixing on Office-31 (ablation)GeT · Office-31average accuracy (%): 84.0 -> 86.0Improved
add GeT to source-only modelResNet-50 · Office-Home UDAmean accuracy (%): 70.2 -> 73.5 (vs ATDOC-NC)Improved
add GeT to CDAN+ECDAN+E · Office-Home UDAmean accuracy (%): 68.5 -> 74.0Improved
use GeT as pseudo-label module for MixMatchMixMatch · Office-31average accuracy (%): 82.9 -> 88.65Improved
add class distribution bias to target domainall methods incl. ATDOC · Office-Home UDA imbalancedaverage accuracy (%): ATDOC-NC 70.2 -> 67.1; GeT 70.2 on imbalancedHurt
GeT versus ATDOC-NC under imbalanced PDAGeT · Office-Home PDA imbalancedaverage accuracy (%): 70.9 -> 75.3Improved
vary mixup coefficient gamma_Q and memory decay gamma_pi (ablation)GeT · A->W imbalanced Office-31average accuracy (%)No clear effect
GeT versus S3D on DomainNet-126 semi-supervised DAGeT · DomainNet-126 SSDAaverage accuracy (%): 69.9 -> 72.2 (1-shot)Improved

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