AI Paper Atlas

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

When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights

You-Wei Luo, Chuan-Xian Ren

TPAMI 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Optimization-based domain generalization · 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 label-shift weighting (GLS) to conditional shift correction (ablation)KECA · Office-Home subsampled source (avg over rates)accuracy (%): 69.9 -> 71.4Improved
add label-shift weighting at 10% subsample rate (ablation)KECA · Office-Home subsampled targetaccuracy (%): 60.6 -> 65.4Improved
add label-shift weighting at 10% subsample rate (ablation)KECA · Office-Home subsampled sourceaccuracy (%): 65.4 -> 66.5Improved
add conditional matching to marginal-only corrections (ablation)label/covariate shift models · Office-Home subsampled sourceaccuracy (%): 57.5 -> 69.9Improved
use label shift model instead of covariate shift model under severe shift (ablation)marginal alignment · Office-Home subsampled source, 10% rateaccuracy (%): 55.3 -> 56.8Improved
use Gaussian instead of linear kernel (ablation)KECA · Office-31 subsampledaccuracy (%): 85.2 -> 86.7Improved
use Gaussian instead of polynomial kernel (ablation)KECA · Office-31 subsampledaccuracy (%): 86.7 -> 86.7No clear effect
use Gaussian instead of Laplacian kernel (ablation)KECA · Office-31 subsampledaccuracy (%): 85.9 -> 86.7Improved
add importance weighting to DANNDANN · Office-Home subsampledaccuracy (%): 51.8 -> 57.6Improved
add importance weighting to CDANCDAN · Office-Home subsampledaccuracy (%): 56.3 -> 61.2Improved
add importance weighting to JANJAN · Office-Home subsampledaccuracy (%): 53.9 -> 55.9Improved
use KECA instead of OSTARKECA · Office-Home subsampledaccuracy (%): 59.5 -> 65.9Improved

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