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 1–25 of 65 papers

Title	Date	Tasks	Status	Hype	Score
AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios	Oct 18, 2024	Anomaly ClassificationAnomaly Detection	CodeCode Available	2	5
OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation	Mar 28, 2024	3D Object DetectionNovel Class Discovery	CodeCode Available	2	5
Spacing Loss for Discovering Novel Categories	Apr 22, 2022	Novel Class Discovery	CodeCode Available	2	5
Open-world Semi-supervised Novel Class Discovery	May 22, 2023	Contrastive LearningNovel Class Discovery	CodeCode Available	1	5
On-the-Fly Category Discovery	Jan 1, 2023	DisentanglementInductive Learning	CodeCode Available	1	5
Parametric Classification for Generalized Category Discovery: A Baseline Study	Nov 21, 2022	ClassificationNovel Class Discovery	CodeCode Available	1	5
MetaGCD: Learning to Continually Learn in Generalized Category Discovery	Aug 21, 2023	Incremental LearningMeta-Learning	CodeCode Available	1	5
Novel Class Discovery for 3D Point Cloud Semantic Segmentation	Mar 21, 2023	2D Semantic SegmentationNovel Class Discovery	CodeCode Available	1	5
Divide and Conquer: Compositional Experts for Generalized Novel Class Discovery	Jan 1, 2022	Novel Class Discovery	CodeCode Available	1	5
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data	Feb 8, 2021	ClusteringMeta-Learning	CodeCode Available	1	5
Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery	Jan 1, 2023	Novel Class Discovery	CodeCode Available	1	5
Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning	Sep 21, 2023	Novel Class DiscoveryOpen-World Semi-Supervised Learning	CodeCode Available	1	5
Class-incremental Novel Class Discovery	Jul 18, 2022	Incremental LearningKnowledge Distillation	CodeCode Available	1	5
Class-relation Knowledge Distillation for Novel Class Discovery	Jul 18, 2023	Knowledge DistillationNovel Class Discovery	CodeCode Available	1	5
Learning to Discover and Detect Objects	Oct 19, 2022	Novel Class DiscoveryNovel Object Detection	CodeCode Available	1	5
A Unified Objective for Novel Class Discovery	Aug 19, 2021	Novel Class DiscoveryNovel Object Detection	CodeCode Available	1	5
AutoNovel: Automatically Discovering and Learning Novel Visual Categories	Jun 29, 2021	ClusteringImage Clustering	CodeCode Available	1	5
Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery	Mar 28, 2023	Novel Class DiscoveryNovel Concepts	CodeCode Available	1	5
Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery	Oct 7, 2022	Novel Class Discovery	CodeCode Available	1	5
Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation	Jul 17, 2024	ClusteringNovel Class Discovery	CodeCode Available	1	5
Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images	Aug 9, 2020	AnatomyAnomaly Detection	CodeCode Available	1	5
Enhancing Novel Object Detection via Cooperative Foundational Models	Nov 19, 2023	Novel Class DiscoveryNovel Object Detection	CodeCode Available	1	5
Novel Class Discovery for Ultra-Fine-Grained Visual Categorization	May 10, 2024	Contrastive LearningFine-Grained Visual Categorization	CodeCode Available	1	5
Neighborhood Contrastive Learning for Novel Class Discovery	Jun 20, 2021	ClusteringContrastive Learning	CodeCode Available	1	5
Novel Class Discovery in Semantic Segmentation	Dec 3, 2021	image-classificationImage Classification	CodeCode Available	1	5

Show:10 25 50

← PrevPage 1 of 3Next →

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