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

ArXi:2603.24106v1 Announce Type: new 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.