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 21–30 of 65 papers

TitleStatusHype
Open-world Machine Learning: A Review and New Outlooks—0
Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling—0
Debiased Novel Category Discovering and Localization—0
PANDAS: Prototype-based Novel Class Discovery and DetectionCode1
Federated Continual Novel Class Learning—0
Novel class discovery meets foundation models for 3D semantic segmentation—0
Enhancing Novel Object Detection via Cooperative Foundational ModelsCode1
A Practical Approach to Novel Class Discovery in Tabular DataCode0
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering—0
Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised LearningCode1
Show:102550
← PrevPage 3 of 7Next →

Benchmark Results

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