Grow and Merge: A Unified Framework for Continuous Categories Discovery Article Swipe

MAKE IMPACT

Xinwei Zhang , Jianwen Jiang , Yutong Feng , Zhi-Fan Wu , Xibin Zhao , Hai Wan , Mingqian Tang , Rong Jin , Yue Gao · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2210.04174

Although a number of studies are devoted to novel category discovery, most of them assume a static setting where both labeled and unlabeled data are given at once for finding new categories. In this work, we focus on the application scenarios where unlabeled data are continuously fed into the category discovery system. We refer to it as the {\bf Continuous Category Discovery} ({\bf CCD}) problem, which is significantly more challenging than the static setting. A common challenge faced by novel category discovery is that different sets of features are needed for classification and category discovery: class discriminative features are preferred for classification, while rich and diverse features are more suitable for new category mining. This challenge becomes more severe for dynamic setting as the system is asked to deliver good performance for known classes over time, and at the same time continuously discover new classes from unlabeled data. To address this challenge, we develop a framework of {\bf Grow and Merge} ({\bf GM}) that works by alternating between a growing phase and a merging phase: in the growing phase, it increases the diversity of features through a continuous self-supervised learning for effective category mining, and in the merging phase, it merges the grown model with a static one to ensure satisfying performance for known classes. Our extensive studies verify that the proposed GM framework is significantly more effective than the state-of-the-art approaches for continuous category discovery.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2210.04174

PDF

https://arxiv.org/pdf/2210.04174

OA Status

green

Cited By

14

Related Works

10

OpenAlex ID

https://openalex.org/W4304701338

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4304701338

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2210.04174

Digital Object Identifier

Title

Grow and Merge: A Unified Framework for Continuous Categories Discovery

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-10-09

Full publication date if available

Authors

Xinwei Zhang, Jianwen Jiang, Yutong Feng, Zhi-Fan Wu, Xibin Zhao, Hai Wan, Mingqian Tang, Rong Jin, Yue Gao

List of authors in order

Landing page

https://arxiv.org/abs/2210.04174

Publisher landing page

PDF URL

https://arxiv.org/pdf/2210.04174

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2210.04174

Direct OA link when available

Concepts

Merge (version control), Discriminative model, Computer science, Machine learning, Artificial intelligence, Categorization, Data mining, Information retrieval

Top concepts (fields/topics) attached by OpenAlex

Cited by

14

Total citation count in OpenAlex

Citations by year (recent)

2025: 1, 2024: 10, 2023: 3

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload