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

Showing 4150 of 65 papers

TitleStatusHype
Novel Class Discovery: an Introduction and Key ConceptsCode0
Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class DiscoveryCode1
On-the-Fly Category DiscoveryCode1
Découvrir de nouvelles classes dans des données tabulairesCode0
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier0
Parametric Classification for Generalized Category Discovery: A Baseline StudyCode1
Learning to Discover and Detect ObjectsCode1
Modeling Inter-Class and Intra-Class Constraints in Novel Class DiscoveryCode1
A Closer Look at Novel Class Discovery from the Labeled Set0
A Method for Discovering Novel Classes in Tabular DataCode0
Show:102550
← PrevPage 5 of 7Next →

Benchmark Results

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