Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Sethi, Simardeep"'
Vision Transformers (ViTs) have demonstrated state-of-the-art performance on many Computer Vision Tasks. Unfortunately, deploying these large-scale ViTs is resource-consuming and impossible for many mobile devices. While most in the community are bui
Externí odkaz:
http://arxiv.org/abs/2305.19365
