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 11–20 of 65 papers

TitleStatusHype
Self-Cooperation Knowledge Distillation for Novel Class Discovery—0
Exclusive Style Removal for Cross Domain Novel Class Discovery—0
Novel Class Discovery for Ultra-Fine-Grained Visual CategorizationCode1
Continual Novel Class Discovery via Feature Enhancement and Adaptation—0
TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen—0
Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation—0
YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery—0
Beyond the Known: Novel Class Discovery for Open-world Graph Learning—0
OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality PropagationCode2
Adaptive Discovering and Merging for Incremental Novel Class Discovery—0
Show:102550
← PrevPage 2 of 7Next →
All datasetsCIFAR10cifar100SVHN

Benchmark Results

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