AI Paper Atlas

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

Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation

Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri, Akshay Kulkarni, Jogendra Nath Kundu, R Venkatesh Babu

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 27 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
add domain-specificity training via query weights (no DRI) (ablation)DSiT vendor-side · Office-Home SSDA (4 settings)average accuracy (%): 74.8 -> 75.6Improved
add domain-representative inputs (patch-shuffled) to domain classifier training (ablation)DSiT vendor-side · Office-Home SSDA (4 settings)average accuracy (%): 75.6 -> 76.6Improved
add domain-specificity training on client side (ablation)SHOT · Office-Home SSDA (4 settings)average accuracy (%): 79.0 -> 80.0Improved
add DRI to client-side domain-specificity training (ablation)DSiT client-side · Office-Home SSDA (4 settings)average accuracy (%): 80.0 -> 81.1Improved
use DRI as a general augmentation for task classifier training with SHOT-B (ablation)SHOT-B · Office-Home SSDA (4 settings)average accuracy (%): 79.1 -> 77.4Hurt
use DRI as a general augmentation for task classifier training with CDTrans (ablation)CDTrans · Office-Home SSDA (4 settings)average accuracy (%): 81.5 -> 76.8Hurt
apply DSiT to source-free adaptation vs SHOT-B on Office-HomeSHOT-B* · Office-Home SSDAaverage accuracy (%): 78.1 -> 80.5Improved
apply DSiT to source-free adaptation vs SHOT-B on DomainNetSHOT-B · DomainNet SSDAaverage accuracy (%): 38.9 -> 42.1Improved
apply DSiT to multi-source source-free adaptationSHOT-B* · Office-Home MSDAaverage accuracy (%): 83.7 -> 84.7Improved
use DSiT instead of non-source-free SSRT-B on Office-HomeSSRT-B · Office-Home SSDAaverage accuracy (%): 85.4 -> 80.5Hurt

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