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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Fan, Xia, Shuyin, Wang, Yi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911555446112256
author Chen, Fan
Xia, Shuyin
Wang, Yi
author_facet Chen, Fan
Xia, Shuyin
Wang, Yi
contents Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit severe distribution shifts. A central issue is stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily disturbed by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this problem, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. The proposed method first groups samples into compact local granular balls and then clusters granular ball centers as representatives to infer pseudo-domains, thereby converting direct sample-level clustering into a hierarchical representative-based clustering process. This design produces more stable and semantically consistent pseudo-domain assignments. On top of the discovered latent domains, we develop a two-branch learning framework that improves transferable semantic representations via semantic codebook re-encoding and captures domain-specific appearance variations through a style branch, thereby alleviating semantic--style entanglement under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol verify the effectiveness of the proposed method and show strong generalization ability, especially in transfer settings with large domain gaps.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24106
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting
Chen, Fan
Xia, Shuyin
Wang, Yi
Computer Vision and Pattern Recognition
Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit severe distribution shifts. A central issue is stable latent domain discovery: directly performing flat clustering on evolving sample-level latent features is easily disturbed by feature noise, outliers, and representation drift, leading to unreliable pseudo-domain assignments and weakened domain-structured learning. To address this problem, we propose a granular ball guided stable latent domain discovery framework for domain-general crowd counting. The proposed method first groups samples into compact local granular balls and then clusters granular ball centers as representatives to infer pseudo-domains, thereby converting direct sample-level clustering into a hierarchical representative-based clustering process. This design produces more stable and semantically consistent pseudo-domain assignments. On top of the discovered latent domains, we develop a two-branch learning framework that improves transferable semantic representations via semantic codebook re-encoding and captures domain-specific appearance variations through a style branch, thereby alleviating semantic--style entanglement under domain shifts. Extensive experiments on ShanghaiTech A/B, UCF\_QNRF, and NWPU-Crowd under a strict no-adaptation protocol verify the effectiveness of the proposed method and show strong generalization ability, especially in transfer settings with large domain gaps.
title Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.24106