AI Paper Atlas

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

Local Context-Aware Active Domain Adaptation

Tao Sun, Cheng Lu, Haibin Ling

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 14 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 diverse (clustered) selection from the top uncertain candidates (ablation)LADA · Office-Home (5% budget)accuracy (%): 72.6 -> 75.3Improved
add progressive anchor set augmentation with confident neighbors (ablation)LADA · Office-Home (5% budget)accuracy (%): 75.3 -> 77.9Improved
add RandAug mixed images to anchor set training (ablation)LADA · Office-Home (5% budget)accuracy (%): 79.5 -> 80.0Improved
add class balancing rejection (CBR) (ablation)LADA · Office-Home RSUT (10% budget)per-class average accuracy (%): 74.3 -> 75.3Improved
replace LI score with entropy, margin, confidence or NAU in LAS (ablation)LAS · Office-Home and Office-31accuracy (%)Improved
increase oversampling ratio M for diverse sampling (ablation)LAS · Office-Home and Office-31accuracy (%)Improved
choose confident samples from the neighborhood of queried data (LAA) instead of randomly (RAA) under larger domain gap (ablation)LADA · DomainNet with added feature displacementaccuracyImproved
use LAA instead of RAA on standard benchmarks (ablation)LAS · Office-Home (10% budget)accuracy (%) avg: 84.9 -> 84.2No clear effect
replace LAA with CDAC after LAS selection (ablation)LADA · Office-Home (10% budget)accuracy (%) avg: 84.2 -> 82.6Hurt
use LAS instead of other selection criteria with MMEMME · Office-Home (5% budget)accuracy (%) avg: 77.2 -> 78.2 (vs MHPL)Improved
use LADA instead of LAMDALADA · Office-Home (10% budget)accuracy (%) avg: 81.9 -> 84.2Improved
use LAS with LAA instead of LAMDA on VisDALADA · VisDA (10% budget)accuracy (%): 91.8 -> 93.1Improved

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