activity
20212024
most citedInstruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion

4 citations · 7 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

1 paper · 1 filter

cs.CV2024

Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter

Yuiko Sakuma, Masakazu Yoshimura, Junji Otsuka +2

Compression of large and performant vision foundation models (VFMs) into arbitrary bit-wise operations (BitOPs) allows their deployment on various hardware. We propose to fine-tune…