AI Paper Atlas

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

Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation

Xiaofeng Liu, Site Li, Yubin Ge, Pengyi Ye, Jane You, Jun Lu

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 27 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 adversarial loss (ablation)RCGUDA 2sigma · DR UDA (KDR to IDRiD)accuracy (%): 61.5 -> 61.8Improved
add adversarial loss (ablation)RCGUDA 3sigma · CHD UDA (echocardiogram)accuracy (%): 74.5 -> 75.0Improved
add adversarial loss (ablation)RCGUDA 2sigma · Age UDA (MORPH to IMDB-WIKI)accuracy (%): 67.7 -> 68.1Improved
add adversarial loss (ablation)RCGUDA 2sigma · DR UDA (KDR to IDRiD)convergence speed: about 1.2 timesImproved
use Wasserstein loss instead of cross-entropyRCGUDA 2sigma · DR UDA (KDR to IDRiD)accuracy (%): 61.8 -> 62.3Improved
use Wasserstein loss instead of cross-entropyRCGUDA 3sigma · CHD UDA (echocardiogram)accuracy (%): 75.0 -> 75.6Improved
use Wasserstein loss instead of cross-entropyRCGUDA 2sigma · Age UDA (MORPH to IMDB-WIKI)accuracy (%): 68.1 -> 68.3Improved
use two-sigma instead of three-sigma RCG constraintRCGUDA · DR UDA (KDR to IDRiD)accuracy (%): 61.6 -> 61.8Improved
use two-sigma instead of three-sigma RCG constraintRCGUDA · Age UDA (MORPH to IMDB-WIKI)accuracy (%): 67.8 -> 68.1Improved
use three-sigma instead of two-sigma RCG constraintRCGUDA · CHD UDA (echocardiogram)accuracy (%): 74.6 -> 75.0Improved
replace non-ordinal UDA (DG-Net++ + Wasserstein) with RCG priorUDA with disentanglement · DR UDA (KDR to IDRiD)MAE: 0.48 -> 0.41Improved
vary sigma factor between 1.8 and 2.4 (ablation)RCGUDA · Age UDA (MORPH to IMDB-WIKI)QWK: same QWK from 1.8sigma to 2.4sigmaNo clear effect

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