Category Discovery: An Open-World Perspective

• URL: http://arxiv.org/abs/2509.22542v2
• Date: Mon, 29 Sep 2025 08:48:01 GMT
• Title: Category Discovery: An Open-World Perspective
• Authors: Zhenqi He, Yuanpei Liu, Kai Han,
• Abstract summary: Category discovery (CD) is an emerging open-world learning task, which aims at automatically categorizing unlabelled data.<n>We provide a comprehensive review of the literature, and offer detailed analysis and in-depth discussion on different methods.<n>We distill key insights showing that large-scale pretrained backbones, hierarchical and auxiliary cues, and curriculum-style training are all beneficial for category discovery.
• Score: 17.624912732260672
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Category discovery (CD) is an emerging open-world learning task, which aims at automatically categorizing unlabelled data containing instances from unseen classes, given some labelled data from seen classes. This task has attracted significant attention over the years and leads to a rich body of literature trying to address the problem from different perspectives. In this survey, we provide a comprehensive review of the literature, and offer detailed analysis and in-depth discussion on different methods. Firstly, we introduce a taxonomy for the literature by considering two base settings, namely novel category discovery (NCD) and generalized category discovery (GCD), and several derived settings that are designed to address the extra challenges in different real-world application scenarios, including continual category discovery, skewed data distribution, federated category discovery, etc. Secondly, for each setting, we offer a detailed analysis of the methods encompassing three fundamental components, representation learning, label assignment, and estimation of class number. Thirdly, we benchmark all the methods and distill key insights showing that large-scale pretrained backbones, hierarchical and auxiliary cues, and curriculum-style training are all beneficial for category discovery, while challenges remain in the design of label assignment, the estimation of class numbers, and scaling to complex multi-object scenarios. Finally, we discuss the key insights from the literature so far and point out promising future research directions. We compile a living survey of the category discovery literature at https://github.com/Visual-AI/Category-Discovery.

Related papers

• A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches [6.356364436395916]
  We present the first comprehensive review of class-agnostic counting (CAC) methodologies.<n>We propose a taxonomy to categorize CAC approaches into three paradigms: reference-based, reference-less, and open-world text-guided.<n>We present results on the FSC-147 dataset, setting a leaderboard using gold-standard metrics, and on the CARPK dataset to assess generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-31T14:47:09Z)
• Contextuality Helps Representation Learning for Generalized Category Discovery [5.885208652383516]
  This paper introduces a novel approach to Generalized Category Discovery (GCD) by leveraging the concept of contextuality. Our model integrates two levels of contextuality: instance-level, where nearest-neighbor contexts are utilized for contrastive learning, and cluster-level, employing contrastive learning. The integration of the contextual information effectively improves the feature learning and thereby the classification accuracy of all categories.
  arXiv  Detail & Related papers  (2024-07-29T07:30:41Z)
• A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application [7.595948982978669]
  Continual learning, also known as incremental learning or life-long learning, stands at the forefront of deep learning and AI systems. We present a review of Continual semantic segmentation (CSS), of which the dense prediction peculiarity makes it a challenging, intricate and burgeoning task. We sort out and categorize current CSS models into two main branches including data-replay and data-free sets. We also introduce four CSS specialities with diverse application scenarios and development tendencies.
  arXiv  Detail & Related papers  (2023-10-22T11:53:56Z)
• Association Graph Learning for Multi-Task Classification with Category Shifts [68.58829338426712]
  We focus on multi-task classification, where related classification tasks share the same label space and are learned simultaneously. We learn an association graph to transfer knowledge among tasks for missing classes. Our method consistently performs better than representative baselines.
  arXiv  Detail & Related papers  (2022-10-10T12:37:41Z)
• Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning [68.63910949916209]
  This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. We propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. We conduct extensive experiments on four benchmark datasets and demonstrate the effectiveness and robustness of the proposed method with state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-01T16:34:33Z)
• Class-incremental Novel Class Discovery [76.35226130521758]
  We study the new task of class-incremental Novel Class Discovery (class-iNCD) We propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-07-18T13:49:27Z)
• Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation [16.357091285395285]
  We tackle the problem of grouping unlabelled images from new classes into different semantic partitions. This is a more realistic and challenging setting than conventional semi-supervised learning. We propose a two-branch learning framework for this problem, with one branch focusing on local part-level information and the other branch focusing on overall characteristics.
  arXiv  Detail & Related papers  (2021-07-07T17:14:40Z)
• Deep Learning for Scene Classification: A Survey [48.57123373347695]
  Scene classification is a longstanding, fundamental and challenging problem in computer vision. The rise of large-scale datasets and the renaissance of deep learning techniques have brought remarkable progress in the field of scene representation and classification. This paper provides a comprehensive survey of recent achievements in scene classification using deep learning.
  arXiv  Detail & Related papers  (2021-01-26T03:06:50Z)
• Dataset Bias in Few-shot Image Recognition [57.25445414402398]
  We first investigate the impact of transferable capabilities learned from base categories. Second, we investigate performance differences on different datasets from dataset structures and different few-shot learning methods.
  arXiv  Detail & Related papers  (2020-08-18T14:46:23Z)
• A Survey on Text Classification: From Shallow to Deep Learning [83.47804123133719]
  The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021. We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification.
  arXiv  Detail & Related papers  (2020-08-02T00:09:03Z)
• UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation [52.487469544343305]
  Methods for object detection and segmentation rely on large scale instance-level annotations for training. We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
  arXiv  Detail & Related papers  (2020-06-12T22:45:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.