RWBD: learning robust weighted binary descriptor for image matching
Z Huang, Z Wei, G Zhang - … on Circuits and Systems for Video …, 2017 - ieeexplore.ieee.org
Binary descriptors are drawing increasing interest as they enable faster processing in a
lower memory footprint, which are suitable to large-scale and real-time vision applications …
lower memory footprint, which are suitable to large-scale and real-time vision applications …
Binary-Decomposed Vision Transformer: Compressing and Accelerating Vision Transformer by Binary Decomposition
R Kondo, H Minoura, T Hirakawa… - … on Image Processing …, 2024 - ieeexplore.ieee.org
Vision Transformers (ViTs) have emerged as versatile and high-performance models for
various tasks such as image classification, object detection, and semantic segmentation …
various tasks such as image classification, object detection, and semantic segmentation …
Binary-decomposed DCNN for accelerating computation and compressing model without retraining
R Kamiya, T Yamashita, M Ambai… - Proceedings of the …, 2017 - openaccess.thecvf.com
The ConvNet has a large number of parameters. This is resulting in increasingly long
computation times and large model sizes. To embedding mobile devices, the model size …
computation times and large model sizes. To embedding mobile devices, the model size …
Relatedness determination device, non-transitory tangible computer-readable medium for the same, and relatedness determination method
M Ambai, M Shimizu - US Patent 10,409,886, 2019 - Google Patents
A relatedness determination device includes: a feature vector acquisition portion that
acquires a binarized feature vector; a basis vector acquisition portion that acquires a …
acquires a binarized feature vector; a basis vector acquisition portion that acquires a …
Learning to assign binary weights to binary descriptor
Z Huang, Z Wei, G Zhang - Infrared Technology and …, 2016 - spiedigitallibrary.org
Constructing robust binary local feature descriptors are receiving increasing interest due to
their binary nature, which can enable fast processing while requiring significantly less …
their binary nature, which can enable fast processing while requiring significantly less …
[PDF][PDF] Binarized-DCNN による識別計算の高速化とモデル圧縮
神谷龍司， 山下隆義， 安倍満， 佐藤育郎… - … 学会技術研究報告; 信学 …, 2016 - mprg.jp
あらまし Deep Convolutional Neural Network (DCNN) は, 一般物体認識やセマンティック
セグメンテーション等の様々なタスクにおいて高い認識性能を実現した. DCNN …
セグメンテーション等の様々なタスクにおいて高い認識性能を実現した. DCNN …
行列分解と早期棄却による多クラス物体検出の高速化
黒川貴都， 山内悠祠， 安倍満， 山下隆義… - 研究報告コンピュータ …, 2015 - ipsj.ixsq.nii.ac.jp
論文抄録 物体検出では, 画像をラスタスキャン時に多数の検出ウインドウを検出対象クラスと非
検出対象クラスに識別する必要があるため. 非常に高い計算コストを要する …
検出対象クラスに識別する必要があるため. 非常に高い計算コストを要する …