Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
ECCV Workshop on Computational Aspects of Deep Learning (CADL)
While transformers have begun to dominate many tasks in vision, applying them to large images is still computationally difficult. A large reason for this is that self-attention scales quadratically with the number of tokens, which in turn, scales quadratically with the image size. On larger images (e.g., 1080p), over 60% of the total computation in the network is spent solely on creating and applying attention matrices. We take a step toward solving this issue by introducing Hydra Attention, an extremely efficient attention operation for Vision Transformers (ViTs). Paradoxically, this efficiency comes from taking multi-head attention to its extreme: by using as many attention heads as there are features, Hydra Attention is computationally linear in both tokens and features with no hidden constants, making it significantly faster than standard self-attention in an off-the-shelf ViT-B/16 by a factor of the token count. Moreover, Hydra Attention retains high accuracy on ImageNet and, in some cases, actually improves it.
Yuming Du, Robin Kips, Albert Pumarola, Sebastian Starke, Ali Thabet, Artsiom Sanakoyeu
Lisa Rivalin, Andrew Grier, Tobias Tiecke, Chi Zhou, Doris Gao, Prakriti Choudhury, John Fabian
Shreshth Tuli, Kinga Bojarczuk, Natalija Gucevska, Mark Harman, Xiao-Yu Wang, Graham Wright