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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 31–40 of 65 papers

Title	Date	Tasks	Status	Score
An Interactive Interface for Novel Class Discovery in Tabular Data	Jun 22, 2023	ClusteringNovel Class Discovery	CodeCode Available	5
Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery	Aug 26, 2023	Novel Class Discoveryreinforcement-learning	CodeCode Available	5
NC-NCD: Novel Class Discovery for Node Classification	Jul 25, 2024	ClassificationKnowledge Distillation	CodeCode Available	5
Novel Class Discovery: an Introduction and Key Concepts	Feb 22, 2023	Contrastive LearningNovel Class Discovery	CodeCode Available	5
A Practical Approach to Novel Class Discovery in Tabular Data	Nov 9, 2023	ClusteringNovel Class Discovery	CodeCode Available	5
Supervised Knowledge May Hurt Novel Class Discovery Performance	Jun 6, 2023	Novel Class DiscoverySemantic Similarity	CodeCode Available	5
A Method for Discovering Novel Classes in Tabular Data	Sep 2, 2022	Multi-Task LearningNovel Class Discovery	CodeCode Available	5
Hierarchical novel class discovery for single-cell transcriptomic profiles	Sep 9, 2024	ClusteringNovel Class Discovery	CodeCode Available	5
Novel Class Discovery for Long-tailed Recognition	Aug 6, 2023	Novel Class Discovery	CodeCode Available	5
YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery	Mar 30, 2024	Class-Incremental Object DetectionNovel Class Discovery	—Unverified	0

Show:10 25 50

← PrevPage 4 of 7Next →

All datasets CIFAR10 cifar100 SVHN

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	AutoNovel	Clustering Accuracy	0.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AutoNovel	Clustering Accuracy	0.75	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AutoNovel	Clustering Accuracy	0.95	—	Unverified