AI Paper Atlas

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

CoReS: Compatible Representations via Stationarity

Niccolò Biondi, Federico Pernici, Matteo Bruni, Alberto Del Bimbo

TPAMI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 11 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
replace BCT with CoReS fixed-simplex stationary trainingcompatible training · CIFAR-100/10, 1 upgradeupdate gain (%): 5.9 -> 21.3Improved
CoReS vs BCT at two upgradescompatible training · CIFAR-100/10, 2 upgradesupdate gain (%): 5.2 -> 54.7Improved
CoReS vs BCT at nine upgradescompatible training · CIFAR-100/10, 9 upgradesAC: 0.11 -> 0.51Improved
CoReS vs BCT at nine upgradescompatible training · CASIA-WebFace/LFW, 9 upgradesAC: 0.09 -> 0.58Improved
CoReS vs BCT with one upgradecompatible training · CASIA-WebFace/LFW, 1 upgradeupdate gain (%): 0.29 -> 0.32No clear effect
CoReS vs BCT with two upgradescompatible training · Market1501, 2 upgradesAC: 0.3 -> 1Improved
CoReS vs BCT cross-testcompatible training · GLDv2 1 upgrademAP@100: 0.16 -> 0.20Improved
CoReS vs BCT cross-testcompatible training · MET kNN 1 upgradeaccuracy: 0.54 -> 0.65Improved
add model selection (ablation)CoReS from scratch · CIFAR-100/10, 9 upgradesAC: 0.51 -> 0.53Improved
add model selection to pretrained CoReS (50 classes) (ablation)CoReS · CIFAR-100/10, 9 upgradesAC: 0.67 -> 0.74Improved
pretrain on 50 classes instead of none (ablation)CoReS · CIFAR-100/10, 9 upgradesAC: 0.51 -> 0.67Improved
use different random init at each upgrade instead of same init (ablation)CoReS · CIFAR-100/10, 9 upgradesAC: 0.51 -> 0.45Hurt

Later papers that compared with this method

3 later accepted papers report CORES as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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