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

TL;DR

This paper introduces a hierarchical clustering approach using granular balls for stable latent domain discovery in domain-general crowd counting, improving robustness against noise and outliers.

Contribution

It proposes a novel granular ball guided clustering framework that enhances pseudo-domain stability and a two-branch learning method for better domain generalization.

Findings

Achieves superior performance on multiple crowd counting datasets.

Demonstrates strong generalization in large domain gap transfer scenarios.

Outperforms existing methods under strict no-adaptation protocols.

Abstract

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.