Browse State-of-the-Art › Novel Class Discovery
Novel Class Discovery
39 papers with code · 3 benchmarks · 3 datasets archive 2025-07-28
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.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| cifar10 (1 row) | AutoNovel | AutoNovel: Automatically Discovering and Learning Novel Visual Categories | code | — | Compare |
| cifar100 (1 row) | AutoNovel | AutoNovel: Automatically Discovering and Learning Novel Visual Categories | code | — | Compare |
| SVHN (1 row) | AutoNovel | AutoNovel: Automatically Discovering and Learning Novel Visual Categories | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 65 · with a code link: 39 · where Syntology ran a sample: 15 (12 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (15 of 65 tagged: 12 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 65 of 65, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
9 Nov 2023 2 repositories listedIn particular, the number of novel classes is usually assumed to be known in advance, and their labels are sometimes used to tune hyperparameters.
-
18 Jul 2023 2 repositories listed Syntology official: harvested, nothing ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 1 pointer-only (licence)In addition, to enable a flexible knowledge distillation scheme for each data point in novel classes, we develop a learnable weighting function for the regularization, which adaptively promotes knowledge transfer based…
-
22 Feb 2023 2 repositories listed Syntology 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples)We then give an overview of the different families of approaches, organized by the way they transfer knowledge from the labeled set to the unlabeled set.
-
21 Nov 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples.
-
2 Sep 2022 2 repositories listedIn this paper, we propose TabularNCD, a new method for discovering novel classes in tabular data.
-
18 Oct 2024 1 repository listedPrevious methods directly cluster anomalies but often struggle due to the lack of anomaly-prior knowledge.
-
9 Sep 2024 1 repository listedOne of the major challenges arising from single-cell transcriptomics experiments is the question of how to annotate the associated single-cell transcriptomic profiles.
-
26 Aug 2024 1 repository listedTo overcome these limitations, we propose Text3DAug, a novel approach leveraging generative models for instance augmentation.
-
25 Jul 2024 1 repository listedSWORD achieves this by employing a self-training strategy to learn new categories and preventing the forgetting of old categories through the joint use of feature prototypes and knowledge distillation.
-
17 Jul 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes.
-
10 May 2024 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified (of 13 harvested samples) · 13 pointer-only (licence)To tackle this problem, we devise a Region-Aligned Proxy Learning (RAPL) framework, which comprises a Channel-wise Region Alignment (CRA) module and a Semi-Supervised Proxy Learning (SemiPL) strategy.
-
28 Mar 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities.
-
27 Feb 2024 1 repository listedIn this work, we look at ways to extend a detector trained for a set of base classes so it can i) spot the presence of novel classes, and ii) automatically enrich its repertoire to be able to detect those newly…
-
19 Nov 2023 1 repository listedWe present a novel approach to transform existing closed-set detectors into open-set detectors.
-
21 Sep 2023 1 repository listedIn open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data.
-
26 Aug 2023 1 repository listedWe employed a clustering method with varying constraint conditions, ranging from strict to loose, allowing for the generation of dependable labels for a subset of unlabeled data during the training phase.
-
21 Aug 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples) · 12 pointer-only (licence)The goal is to continually discover novel classes while maintaining the performance in known classes.
-
9 Aug 2023 1 repository listed Syntology official (archive's flag): 1 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)This paper bridges the gap by providing an analytical framework to formalize and investigate when and how known classes can help discover novel classes.
-
6 Aug 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 13 harvested samples) · 13 pointer-only (licence)In this paper, we consider a more realistic setting for novel class discovery where the distributions of novel and known classes are long-tailed.
-
22 Jun 2023 1 repository listedThis task is difficult and can often only be performed by a domain expert.
-
6 Jun 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Next, by using the proposed transfer flow, we conduct various empirical experiments with different levels of semantic similarity, yielding that supervised knowledge may hurt NCD performance.
-
22 May 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed…
-
28 Mar 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners.
-
21 Mar 2023 1 repository listedFirstly, we address the new problem of NCD for point cloud semantic segmentation.
-
1 Jan 2023 1 repository listedNovel Class Discovery (NCD) aims to discover unknown classes without any annotation, by exploiting the transferable knowledge already learned from a base set of known classes.
-
1 Jan 2023 1 repository listedOur code is available at https://github.com/PRIS-CV/On-the-fly-Category-Discovery.
-
28 Nov 2022 1 repository listedIn Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes.
-
19 Oct 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments…
-
7 Oct 2022 1 repository listedSpecifically, we propose an inter-class sKLD constraint to effectively exploit the disjoint relationship between labelled and unlabelled classes, enforcing the separability for different classes in the embedding space.
-
18 Jul 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 6 harvested samples) · 6 pointer-only (licence)We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been…
-
5 Jul 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
22 Apr 2022 1 repository listed
-
1 Jan 2022 1 repository listed
-
3 Dec 2021 1 repository listed
-
19 Aug 2021 1 repository listed Syntology 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 4 harvested samples)
-
29 Jun 2021 1 repository listed
-
20 Jun 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)
-
8 Feb 2021 1 repository listed
-
9 Aug 2020 1 repository listed
-
NeurNCD: Novel Class Discovery via Implicit Neural Representation6 Jun 2025 0 repositories listed
-
DATA: Multi-Disentanglement based Contrastive Learning for Open-World Semi-Supervised Deepfake Attribution7 May 2025 0 repositories listed
-
Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery12 Mar 2025 0 repositories listed
-
Novel Class Discovery for Open Set Raga Classification27 Nov 2024 0 repositories listed
-
OW-Rep: Open World Object Detection with Instance Representation Learning24 Sep 2024 0 repositories listed
-
Self-Cooperation Knowledge Distillation for Novel Class Discovery2 Jul 2024 0 repositories listed
-
Exclusive Style Removal for Cross Domain Novel Class Discovery26 Jun 2024 0 repositories listed
-
Continual Novel Class Discovery via Feature Enhancement and Adaptation10 May 2024 0 repositories listed
-
TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen16 Apr 2024 0 repositories listed
-
Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation16 Apr 2024 0 repositories listed
-
YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery30 Mar 2024 0 repositories listed
-
Beyond the Known: Novel Class Discovery for Open-world Graph Learning29 Mar 2024 0 repositories listed
-
Adaptive Discovering and Merging for Incremental Novel Class Discovery6 Mar 2024 0 repositories listed
-
Open-world Machine Learning: A Review and New Outlooks4 Mar 2024 0 repositories listed
-
Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling2 Mar 2024 0 repositories listed
-
Debiased Novel Category Discovering and Localization29 Feb 2024 0 repositories listed
-
Federated Continual Novel Class Learning21 Dec 2023 0 repositories listed
-
Novel class discovery meets foundation models for 3D semantic segmentation6 Dec 2023 0 repositories listed
-
Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering28 Sep 2023 0 repositories listed
-
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier21 Nov 2022 0 repositories listed
-
A Closer Look at Novel Class Discovery from the Labeled Set19 Sep 2022 0 repositories listed
-
Novel Class Discovery without Forgetting21 Jul 2022 0 repositories listed
-
Mutual Information-guided Knowledge Transfer for Novel Class Discovery24 Jun 2022 0 repositories listed
-
Open Set Domain Adaptation By Novel Class Discovery7 Mar 2022 0 repositories listed
-
Open-Set Representation Learning through Combinatorial Embedding29 Jun 2021 0 repositories listed
-
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World12 Apr 2020 0 repositories listed
Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections