4 citations · 7 across the 4 of their papers we have counts for
4 papers · 1 filter
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…
Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion
Hiromichi Kamata, Yuiko Sakuma, Akio Hayakawa +2
We propose a high-quality 3D-to-3D conversion method, Instruct 3D-to-3D. Our method is designed for a novel task, which is to convert a given 3D scene to another scene according to…
DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter
Yuiko Sakuma, Masato Ishii, Takuya Narihira
We address the challenge of training a large supernet for the object detection task, using a relatively small amount of training data. Specifically, we propose an efficient superne…
n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization
Yuiko Sakuma, Hiroshi Sumihiro, Jun Nishikawa +2
Powers-of-two (PoT) quantization reduces the number of bit operations of deep neural networks on resource-constrained hardware. However, PoT quantization triggers a severe accuracy…