Research

Paper

TESTING March 25, 2026

Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting

Authors

Fan Chen, Shuyin Xia, Yi Wang, Xinbo Gao

Abstract

Single-source domain generalization for crowd counting remains highly challenging because a single labeled source domain often contains heterogeneous latent domains, while test data may exhibit severe distribution shifts. A fundamental difficulty lies in stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily affected by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this issue, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. Specifically, the proposed method first organizes samples into compact local granular balls and then clusters granular ball centers as representatives to obtain pseudo-domains, transforming direct sample-level clustering into a hierarchical representative-based clustering process. This design yields more stable and semantically consistent pseudo-domain assignments. Built upon the discovered latent domains, we further develop a two-branch learning framework that enhances transferable semantic representations via semantic codebook re-encoding while modeling domain-specific appearance variations through a style branch, thereby reducing semantic--style entanglement and improving generalization under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol demonstrate that the proposed method consistently outperforms strong baselines, especially under large domain gaps.

Metadata

arXiv ID: 2603.24106
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24106v1</id>\n    <title>Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting</title>\n    <updated>2026-03-25T09:12:35Z</updated>\n    <link href='https://arxiv.org/abs/2603.24106v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24106v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Single-source domain generalization for crowd counting remains highly challenging because a single labeled source domain often contains heterogeneous latent domains, while test data may exhibit severe distribution shifts. A fundamental difficulty lies in stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily affected by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this issue, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. Specifically, the proposed method first organizes samples into compact local granular balls and then clusters granular ball centers as representatives to obtain pseudo-domains, transforming direct sample-level clustering into a hierarchical representative-based clustering process. This design yields more stable and semantically consistent pseudo-domain assignments. Built upon the discovered latent domains, we further develop a two-branch learning framework that enhances transferable semantic representations via semantic codebook re-encoding while modeling domain-specific appearance variations through a style branch, thereby reducing semantic--style entanglement and improving generalization under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol demonstrate that the proposed method consistently outperforms strong baselines, especially under large domain gaps.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-25T09:12:35Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Fan Chen</name>\n    </author>\n    <author>\n      <name>Shuyin Xia</name>\n    </author>\n    <author>\n      <name>Yi Wang</name>\n    </author>\n    <author>\n      <name>Xinbo Gao</name>\n    </author>\n  </entry>"
}