Search Results for author: Rio Yokota

Found 16 papers, 11 papers with code

Pre-training Vision Transformers with Very Limited Synthesized Images

1 code implementation27 Jul 2023 Ryo Nakamura, Hirokatsu Kataoka, Sora Takashima, Edgar Josafat Martinez Noriega, Rio Yokota, Nakamasa Inoue

Prior work on FDSL has shown that pre-training vision transformers on such synthetic datasets can yield competitive accuracy on a wide range of downstream tasks.

Data Augmentation

ASDL: A Unified Interface for Gradient Preconditioning in PyTorch

2 code implementations8 May 2023 Kazuki Osawa, Satoki Ishikawa, Rio Yokota, Shigang Li, Torsten Hoefler

Gradient preconditioning is a key technique to integrate the second-order information into gradients for improving and extending gradient-based learning algorithms.

Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves

no code implementations CVPR 2023 Sora Takashima, Ryo Hayamizu, Nakamasa Inoue, Hirokatsu Kataoka, Rio Yokota

Unlike JFT-300M which is a static dataset, the quality of synthetic datasets will continue to improve, and the current work is a testament to this possibility.

Informative Sample-Aware Proxy for Deep Metric Learning

no code implementations18 Nov 2022 Aoyu Li, Ikuro Sato, Kohta Ishikawa, Rei Kawakami, Rio Yokota

Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies.

Metric Learning Retrieval

Replacing Labeled Real-image Datasets with Auto-generated Contours

no code implementations CVPR 2022 Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota

In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k without the use of real images, human-, and self-supervision during the pre-training of Vision Transformers (ViTs).

Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime

no code implementations29 Sep 2021 Hiroki Naganuma, Taiji Suzuki, Rio Yokota, Masahiro Nomura, Kohta Ishikawa, Ikuro Sato

Generalization measures are intensively studied in the machine learning community for better modeling generalization gaps.

Hyperparameter Optimization

RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering

1 code implementation ICCV 2021 Shun Iwase, Xingyu Liu, Rawal Khirodkar, Rio Yokota, Kris M. Kitani

Furthermore, we utilize differentiable Levenberg-Marquardt (LM) optimization to refine a pose fast and accurately by minimizing the feature-metric error between the input and rendered image representations without the need of zooming in.

6D Pose Estimation 6D Pose Estimation using RGB

Epipolar-Guided Deep Object Matching for Scene Change Detection

no code implementations30 Jul 2020 Kento Doi, Ryuhei Hamaguchi, Shun Iwase, Rio Yokota, Yutaka Matsuo, Ken Sakurada

To cope with the difficulty, we introduce a deep graph matching network that establishes object correspondence between an image pair.

Change Detection Graph Matching +1

Scalable and Practical Natural Gradient for Large-Scale Deep Learning

1 code implementation13 Feb 2020 Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size.

Image Classification

Effect of Mixed Precision Computing on H-Matrix Vector Multiplication in BEM Analysis

1 code implementation30 Oct 2019 Rise Ooi, Takeshi Iwashita, Takeshi Fukaya, Akihiro Ida, Rio Yokota

Hierarchical Matrix (H-matrix) is an approximation technique which splits a target dense matrix into multiple submatrices, and where a selected portion of submatrices are low-rank approximated.

Mathematical Software Distributed, Parallel, and Cluster Computing

Practical Deep Learning with Bayesian Principles

1 code implementation NeurIPS 2019 Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan

Importantly, the benefits of Bayesian principles are preserved: predictive probabilities are well-calibrated, uncertainties on out-of-distribution data are improved, and continual-learning performance is boosted.

Continual Learning Data Augmentation +1

Extreme Scale FMM-Accelerated Boundary Integral Equation Solver for Wave Scattering

1 code implementation27 Mar 2018 Mustafa Abduljabbar, Mohammed Al Farhan, Noha Al-Harthi, Rui Chen, Rio Yokota, Hakan Bagci, David Keyes

With distributed memory optimizations, on the other hand, we report near-optimal efficiency in the weak scalability study with respect to both the logarithmic communication complexity as well as the theoretical scaling complexity of FMM.

Performance Computational Engineering, Finance, and Science Mathematical Software

Asynchronous Execution of the Fast Multipole Method Using Charm++

1 code implementation29 May 2014 Mustafa AbdulJabbar, Rio Yokota, David Keyes

Fast multipole methods (FMM) on distributed mem- ory have traditionally used a bulk-synchronous model of com- municating the local essential tree (LET) and overlapping it with computation of the local data.

Distributed, Parallel, and Cluster Computing 70F10 D.1.2; D.1.3; G.1.0; G.1.2

Cannot find the paper you are looking for? You can Submit a new open access paper.