Learning to count small and clustered objects with application to bacterial colonies

ArXi:2604.20030v1 Announce Type: new Automated bacterial colony counting from images is an important technique to obtain data required for the development of vaccines and antibiotics. However, bacterial colonies present unique machine vision challenges that affect counting, including (1) small physical size, (2) object clustering, (3) high data annotation cost, and (4) limited cross-species generalisation.