AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Gradient Extrapolation for Debiased Representation Learning

Ihab Asaad, Maha Shadaydeh, Joachim Denzler

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 5 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
raise extrapolation factor beta from -1 (equivalent to biased loss) to 0 and 1 (ablation)GERNE · C-MNIST 0.5% minority (known)unbiased test accuracyImproved
use beta=1 instead of beta=0 (ablation)GERNE · C-MNIST 0.5% minority (known)generalizationImproved
increase beta to 1.2, near upper bound 1.22 (ablation)GERNE · C-MNIST 0.5% minority (known)training stabilityHurt
use GERNE extrapolated gradient instead of resamplingResampling · bFFHQ (known attributes)accuracy: 72.13 -> 85.20Improved
use GERNE instead of Group DROGroup DRO · C-MNIST (1% minority, known)accuracy: 68.78 -> 84.47Improved
use GERNE instead of Group DROGroup DRO · C-CIFAR-10 (5% minority, known)accuracy: 57.32 -> 62.40Improved
use GERNE instead of LC with unknown attributesLC · C-MNIST (5% minority, unknown)accuracy: 91.16 -> 90.98Hurt
lower pseudo-minority threshold t to 5e-4 (about 28 samples) (ablation)GERNE unknown attrs · C-MNIST 0.5% minoritytest accuracy: approximately 70%Mixed
use higher threshold t=1e-2 for pseudo-minority group (ablation)GERNE unknown attrs · C-MNIST 0.5% minoritybest betaHurt
use group-balanced validation set versus validation without attributes (ablation)GERNE · CelebAworst-group accuracy: 86.28 -> 74.24Hurt
train GERNE on validation set instead of DFR last-layer trainingDFR · CelebAworst-group test accuracy: 86.30 -> 90.97Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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