AI Paper Atlas

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

Discriminative Noise Robust Sparse Orthogonal Label Regression-Based Domain Adaptation

Lingkun Luo, Shiqiang Hu, Liming Chen

IJCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 9 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 discriminative force terms (CDDA+) to JDA (ablation)JDA · CMU PIEaccuracy: 60.24 -> 63.22Improved
add NRS_OLR term to JDA (JOLR-DA) (ablation)JDA · CMU PIEaccuracy: 60.24 -> 69.96Improved
jointly add discriminative force and NRS_OLR (DOLL-DA) (ablation)JDA · CMU PIEaccuracy: 60.24 -> 82.50Improved
add data distribution alignment to OLR classifier (ablation)OLR · CMU PIEaccuracy: 55.88 -> 60.24Improved
add discriminative force terms only (ablation)JDA · Office-Homeaccuracy: +0.19 pointNo clear effect
add NRS_OLR term to JDA (ablation)JDA · Office-Homeaccuracy: 44.48Improved
add NRS_OLR to CDDA+ (full DOLL-DA) (ablation)CDDA+ · Office-Homeaccuracy: +11.07 pointsImproved
add discriminative force terms (ablation)JDA · USPS+MNIST (shallow)accuracy: 69.14Improved
jointly add both terms (DOLL-DA) (ablation)JDA · USPS+MNIST (shallow)accuracy: 77.82Improved
use shallow-feature DOLL-DA versus deep DANNDANN · USPS+MNISTaccuracy: +2 pointsImproved
jointly add both terms (DOLL-DA) (ablation)JDA · SVHN-MNISTaccuracy: +22 pointsImproved
jointly add both terms (DOLL-DA) (ablation)JDA · Office+Caltech (SURF)accuracy: 51.18Improved

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