Scaling Vision with Sparse Mixture of Experts

06/10/2021 ∙ by Carlos Riquelme, et al. ∙ 6

Sparsely-gated Mixture of Experts networks (MoEs) have demonstrated excellent scalability in Natural Language Processing. In Computer Vision, however, almost all performant networks are "dense", that is, every input is processed by every parameter. We present a Vision MoE (V-MoE), a sparse version of the Vision Transformer, that is scalable and competitive with the largest dense networks. When applied to image recognition, V-MoE matches the performance of state-of-the-art networks, while requiring as little as half of the compute at inference time. Further, we propose an extension to the routing algorithm that can prioritize subsets of each input across the entire batch, leading to adaptive per-image compute. This allows V-MoE to trade-off performance and compute smoothly at test-time. Finally, we demonstrate the potential of V-MoE to scale vision models, and train a 15B parameter model that attains 90.35 ImageNet.



There are no comments yet.


page 6

page 31

page 32

page 33

page 36

page 41

page 42

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.