AI RESEARCH

CountFormer: A Transformer Framework for Learning Visual Repetition and Structure in Class-Agnostic Object Counting

arXiv CS.CV

ArXi:2510.23785v2 Announce Type: replace Humans can often count unfamiliar objects by observing visual repetition and composition, rather than relying only on object categories. However, many exemplar-free counting models struggle in such situations and may overcount when objects contain symmetric components, repeated substructures, or partial occlusion. We