AI Paper Atlas

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

SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 126 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 consistency-based selective entropy minimization instead of minimizing entropy on all target instances (ablation)SENTRY · DomainNet C->Sper-class accuracy: 68.8 -> 79.5Improved
add consistency-based selection (instead of all instances) (ablation)SENTRY · OfficeHome RS-UT Rw->Clper-class accuracy: 44.9 -> 56.8Improved
add entropy maximization on inconsistent instances (ablation)SENTRY · DomainNet C->Sper-class accuracy: 77.7 -> 79.5Improved
add entropy maximization on inconsistent instances (ablation)SENTRY · OfficeHome RS-UT Rw->Clper-class accuracy: 55.3 -> 56.8Improved
add entropy maximization on incorrect instances (oracle selection) (ablation)SENTRY oracle · DomainNet C->Sper-class accuracy: 84.3 -> 86.3Improved
add entropy maximization on incorrect instances (oracle selection) (ablation)SENTRY oracle · OfficeHome RS-UT Rw->Clper-class accuracy: 77.7 -> 80.1Improved
use majority instead of unanimous voting (ablation)SENTRY · DomainNet C->Sper-class accuracy: 77.8 -> 79.5Improved
use majority instead of unanimous voting (ablation)SENTRY · OfficeHome RS-UT Rw->Clper-class accuracy: 52.2 -> 56.8Improved
vary committee size k and RandAugment transforms N (ablation)SENTRY · DomainNet C->Sper-class accuracy: 76.8 to 79.5No clear effect
backpropagate on augmented rather than original target instances (ablation)SENTRY · DomainNet C->Sper-class accuracy: 73.1 -> 79.5Improved
add pseudo class-balanced target sampling (ablation)SENTRY · DomainNet C->Sper-class accuracy: 76.6 -> 78.6Improved
add source class-balanced sampling (ablation)SENTRY · DomainNet C->Sper-class accuracy: 76.6 -> 77.1Improved

Later papers that compared with this method

10 later accepted papers report SENTRY as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.

2 more not listed.

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