Novel Class Discovery

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.

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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 39 papers with code (65 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• A Practical Approach to Novel Class Discovery in Tabular Data
  9 Nov 2023 2 repositories listed
  In particular, the number of novel classes is usually assumed to be known in advance, and their labels are sometimes used to tune hyperparameters.
• Class-relation Knowledge Distillation for Novel Class Discovery
  18 Jul 2023 2 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 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…
• Novel Class Discovery: an Introduction and Key Concepts
  22 Feb 2023 2 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  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.
• Parametric Classification for Generalized Category Discovery: A Baseline Study
  21 Nov 2022 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples.
• A Method for Discovering Novel Classes in Tabular Data
  2 Sep 2022 2 repositories listed
  In this paper, we propose TabularNCD, a new method for discovering novel classes in tabular data.
• AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios
  18 Oct 2024 1 repository listed
  Previous methods directly cluster anomalies but often struggle due to the lack of anomaly-prior knowledge.
• Hierarchical novel class discovery for single-cell transcriptomic profiles
  9 Sep 2024 1 repository listed
  One of the major challenges arising from single-cell transcriptomics experiments is the question of how to annotate the associated single-cell transcriptomic profiles.
• Text3DAug -- Prompted Instance Augmentation for LiDAR Perception
  26 Aug 2024 1 repository listed
  To overcome these limitations, we propose Text3DAug, a novel approach leveraging generative models for instance augmentation.
• NC-NCD: Novel Class Discovery for Node Classification
  25 Jul 2024 1 repository listed
  SWORD 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.
• Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation
  17 Jul 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 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.
• Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
  10 May 2024 1 repository listed Syntology ran 12 of 13 samples · 1 unverified · 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.
• OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation
  28 Mar 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities.
• PANDAS: Prototype-based Novel Class Discovery and Detection
  27 Feb 2024 1 repository listed
  In 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…
• Enhancing Novel Object Detection via Cooperative Foundational Models
  19 Nov 2023 1 repository listed
  We present a novel approach to transform existing closed-set detectors into open-set detectors.
• Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning
  21 Sep 2023 1 repository listed
  In 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.
• Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery
  26 Aug 2023 1 repository listed
  We 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.
• MetaGCD: Learning to Continually Learn in Generalized Category Discovery
  21 Aug 2023 1 repository listed Syntology ran 6 of 12 samples · 6 unverified · 12 pointer-only (licence)
  The goal is to continually discover novel classes while maintaining the performance in known classes.
• When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
  9 Aug 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 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.
• Novel Class Discovery for Long-tailed Recognition
  6 Aug 2023 1 repository listed Syntology ran 7 of 13 samples · 6 unverified · 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.
• An Interactive Interface for Novel Class Discovery in Tabular Data
  22 Jun 2023 1 repository listed
  This task is difficult and can often only be performed by a domain expert.
• Supervised Knowledge May Hurt Novel Class Discovery Performance
  6 Jun 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  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.
• Open-world Semi-supervised Novel Class Discovery
  22 May 2023 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 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…
• Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
  28 Mar 2023 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners.
• Novel Class Discovery for 3D Point Cloud Semantic Segmentation
  21 Mar 2023 1 repository listed
  Firstly, we address the new problem of NCD for point cloud semantic segmentation.
• On-the-Fly Category Discovery
  1 Jan 2023 1 repository listed
  Our code is available at https://github.
• Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery
  1 Jan 2023 1 repository listed
  Novel 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.
• Découvrir de nouvelles classes dans des données tabulaires
  28 Nov 2022 1 repository listed
  In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes.
• Learning to Discover and Detect Objects
  19 Oct 2022 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  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,…
• Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery
  7 Oct 2022 1 repository listed
  Specifically, 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.
• Class-incremental Novel Class Discovery
  18 Jul 2022 1 repository listed Syntology ran 2 of 6 samples · 4 unverified · 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…

Syntology lines on 14 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. Read from the graph 2026-09-24.