AI Paper Atlas

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

Boosting Open Set Recognition Performance through Modulated Representation Learning

Amit Kumar Kundu, Vaishnavi S Patil, Joseph JaJa

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 2 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
increase temperature during training (low to high) instead of constant (ablation)CE loss · CUB Hard splitAUROC: 74.98 -> 78.08Improved
decrease temperature during training (linear decrease or M-CosSch) instead of increasing (ablation)CE loss · CUBaccuracy: 84.43 -> 81.64Hurt
random temperature each epoch (ablation)CE loss · TinyImageNetAUROC: 82.85 -> 78.37Hurt
add M-NegCosSch to SupCon lossSupCon · CUBaccuracy: 83.43 -> 85.3Improved
add NegCosSch to ARPL lossARPL · SCarsaccuracy: 97.37 -> 97.29No clear effect
add NegCosSch to CE+LSCE with label smoothing · TinyImageNetaccuracy: 84.55 -> 84.24Mixed
add NegCosSch on a pretrained Tiny ViTCE loss · CUBaccuracy: 90.83 -> 91.2Improved
vary period P (100 vs 200) of NegCosSch (ablation)SupCon NegCosSch · TinyImageNetAUROC: 82.91 -> 83.09No clear effect
increase delay k from 0 to 1 in generalized cosine schedule (ablation)SupCon GCosSch · TinyImageNetAUROC: 82.87 -> 83.09Improved
add NegCosSch to ProtoCon lossProtoCon · TinyImageNetOSCR: 70.53 -> 71.12Improved
add NegCosSch on CIFAR benchmarksSupCon · CIFAR10, CIFAR+10, CIFAR+50AUROC: 94.04 -> 94.10No clear effect
train with more known classes while using NegCosSch (ablation)CE NegCosSch · SSBsimprovement over best constantImproved

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