Author name: Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Oscar Mendez, Dacheng Tao, Xuelong Li

arXiv:2604.18842v1 Announce Type: new
Abstract: Human perception generalizes well across different domains, but most vision models struggle beyond their training data. This gap motivates multi-dataset learning, where a single model is trained on diver…