AI Paper Atlas

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

Burn after Reading: Online Adaptation for Cross-Domain Streaming Data

Luyu Yang, Mingfei Gao, Zeyuan Chen, Ran Xu, Abhinav Shrivastava, Chetan Ramaiah

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 1 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 cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · VisDA-C (online)online average accuracy: 78.5 -> 79.4Improved
add cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · COVID-DAonline average accuracy: 94.4 -> 96.5Improved
add cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · WILDS-Camelyon17online average accuracy: 86.2 -> 89.2Improved
add cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · Fashion-MNIST to DeepFashiononline average accuracy: 42.3 -> 49.1Improved
add cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · WILDS-Camelyon17one-pass accuracy: 89.4 -> 91.9Improved
add cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · Fashion-MNIST to DeepFashionone-pass accuracy: 39.9 -> 46.3Improved
add cross-domain bootstrapping with two co-supervised learners (ablation)single-learner baseline · VisDA-C and COVID-DAone-pass accuracy: 84.0 -> 84.0No clear effect
add entropy minimization term (ablation)single-learner baseline · VisDA-Conline average accuracy: 63.7 -> 78.5Improved
add class-balancing diversity term (ablation)single-learner baseline · VisDA-Cone-pass accuracy: 73.0 -> 84.0Improved
use FixMatch for both learners instead of MixMatch for one (ablation)CroDoBo · VisDA-Conline average accuracy: 74.3 -> 79.4Improved
use FixMatch-style l_t instead of MixMatch (ablation)single-learner baseline · VisDA-Conline average accuracy: 76.3 -> 78.5Improved
apply RandAugment on entropy and diversity terms (ablation)single-learner baseline · VisDA-Conline average accuracy: 78.5 -> 77.6Hurt

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