AI Paper Atlas

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

Towards Accurate Open-Set Recognition via Background-Class Regularization

Wonwoo Cho, Jaegul Choo

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 16 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 class-inclusion background-class regularization to distance-based classifier (ablation)distance-based classifier · CIFAR10 (Setting 1)AUROC: 0.757 -> 0.948Improved
add class-inclusion regularization (ablation)distance-based classifier · TinyImageNet (Setting 1)OSCR: 0.315 -> 0.493Improved
add L_bg,k term for correctly classified KKC data (ablation)class-inclusion BCR · CIFAR10 (Setting 1)OSCR: 0.509 -> 0.870Improved
use class-inclusion loss instead of HSC-based L_bg (ablation)BCR · CIFAR10 (Setting 1)AUROC: 0.634 -> 0.948Improved
use class-inclusion loss instead of triplet loss (ablation)BCR · CIFAR10 (Setting 1)AUROC: 0.860 -> 0.936Improved
use class-inclusion loss instead of triplet loss (ablation)BCR · TinyImageNet (Setting 1)OSCR: 0.423 -> 0.493Improved
raise lambda from 5 to 10 (ablation)class-inclusion BCR · TinyImageNet (Setting 1)OSCR: 0.480 -> 0.361Hurt
vary lambda within 1 to 5 (ablation)class-inclusion BCR · CIFAR10 (Setting 1)accuracy: 0.973 / 0.973No clear effect
use class-inclusion loss instead of uniformity lossSoftmax BCR · CIFAR100 (Setting 2)OSCR: 0.685 -> 0.720Improved
use class-inclusion loss instead of Energy lossSoftmax BCR · SVHN (Setting 1)AUROC: 0.911 -> 0.956Improved
use class-inclusion loss instead of uniformity loss for textGRU text classifier · 20 Newsgroups vs IMDBAUROC: 0.805 -> 0.999Improved
use class-inclusion loss instead of Objectosphere lossSoftmax BCR · CIFAR10 (Setting 1)OSCR: 0.851 -> 0.870Improved

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