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 6165 of 65 papers

TitleStatusHype
Self-Cooperation Knowledge Distillation for Novel Class Discovery0
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering0
TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen0
Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation0
A Closer Look at Novel Class Discovery from the Labeled Set0
Show:102550
← PrevPage 7 of 7Next →

Benchmark Results

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