1 code implementation • 7 Nov 2020 • Guoqing Bao, Manuel B. Graeber, Xiuying Wang
We have carried out the experiment on four benchmark datasets, i. e. Cifar-10, Cifar-100, STL-10 and ImageNet32x32, using five popular CNN models, Multiception achieved accuracy promotion in all models and demonstrated higher accuracy performance compared to related works.