SOTAVerified

Novel Class Discovery

The goal of Novel Class Discovery (NCD) is to identify new classes in unlabeled data, by exploiting prior knowledge from known classes. In this specific setup, the data is split in two sets. The first is a labeled set containing known classes and the second is an unlabeled set containing unknown classes that must be discovered.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–65 of 65 papers

TitleStatusHype
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering—0
Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class DiscoveryCode0
Novel Class Discovery for Long-tailed RecognitionCode0
An Interactive Interface for Novel Class Discovery in Tabular DataCode0
Supervised Knowledge May Hurt Novel Class Discovery PerformanceCode0
Novel Class Discovery: an Introduction and Key ConceptsCode0
Découvrir de nouvelles classes dans des données tabulairesCode0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier—0
A Closer Look at Novel Class Discovery from the Labeled Set—0
A Method for Discovering Novel Classes in Tabular DataCode0
Novel Class Discovery without Forgetting—0
Mutual Information-guided Knowledge Transfer for Novel Class Discovery—0
Open Set Domain Adaptation By Novel Class Discovery—0
Open-Set Representation Learning through Combinatorial Embedding—0
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World—0
Show:102550
← PrevPage 2 of 2Next →
All datasetsCIFAR10cifar100SVHN

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AutoNovelClustering Accuracy0.92—Unverified
#ModelMetricClaimedVerifiedStatus
1AutoNovelClustering Accuracy0.75—Unverified
#ModelMetricClaimedVerifiedStatus
1AutoNovelClustering Accuracy0.95—Unverified