NVIDIA’s AdaViT Halts Token Computation to Adaptively Adjust ViT Inference Cost on Images of Different Complexity
Nvidia researchers propose AdaViT, an input-dependent mechanism that adaptively adjusts vision transformers’ inference cost by halting the compute of different tokens at different depths to reserve...
Source: syncedreview.com
Nvidia researchers propose AdaViT, an input-dependent mechanism that adaptively adjusts vision transformers’ inference cost by halting the compute of different tokens at different depths to reserve compute for discriminative tokens.