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
NeurNCD: Novel Class Discovery via Implicit Neural Representation—0
Novel Class Discovery for Open Set Raga Classification—0
Novel class discovery meets foundation models for 3D semantic segmentation—0
Novel Class Discovery without Forgetting—0
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World—0
Open Set Domain Adaptation By Novel Class Discovery—0
Open-Set Representation Learning through Combinatorial Embedding—0
Open-world Machine Learning: A Review and New Outlooks—0
OW-Rep: Open World Object Detection with Instance Representation Learning—0
Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling—0
Self-Cooperation Knowledge Distillation for Novel Class Discovery—0
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering—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
A Closer Look at Novel Class Discovery from the Labeled Set—0
Show:102550
← PrevPage 3 of 3Next →
All datasetsCIFAR10cifar100SVHN

Benchmark Results

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