Search Results for author: Shuji Suzuki

Found 9 papers, 2 papers with code

A Scaling Law for Syn-to-Real Transfer: How Much Is Your Pre-training Effective?

no code implementations29 Sep 2021 Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi

Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks.

Image Generation Transfer Learning

A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?

1 code implementation25 Aug 2021 Hiroaki Mikami, Kenji Fukumizu, Shogo Murai, Shuji Suzuki, Yuta Kikuchi, Taiji Suzuki, Shin-ichi Maeda, Kohei Hayashi

Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks.

Image Generation Transfer Learning

An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation

no code implementations11 May 2020 Yuta Tokuoka, Shuji Suzuki, Yohei Sugawara

To evaluate the applicability of the ITL approach, we adopted the brain tissue annotation label on the source domain dataset of Magnetic Resonance Imaging (MRI) images to the task of brain tumor segmentation on the target domain dataset of MRI.

Brain Tumor Segmentation Segmentation +3

Team PFDet's Methods for Open Images Challenge 2019

no code implementations25 Oct 2019 Yusuke Niitani, Toru Ogawa, Shuji Suzuki, Takuya Akiba, Tommi Kerola, Kohei Ozaki, Shotaro Sano

Using this method, the team PFDet achieved 3rd and 4th place in the instance segmentation and the object detection track, respectively.

Instance Segmentation Object +4

Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects

no code implementations CVPR 2019 Yusuke Niitani, Takuya Akiba, Tommi Kerola, Toru Ogawa, Shotaro Sano, Shuji Suzuki

However, large datasets like Open Images Dataset v4 (OID) are sparsely annotated, and some measure must be taken in order to ensure the training of a reliable detector.

object-detection Object Detection

Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes

no code implementations12 Nov 2017 Takuya Akiba, Shuji Suzuki, Keisuke Fukuda

We demonstrate that training ResNet-50 on ImageNet for 90 epochs can be achieved in 15 minutes with 1024 Tesla P100 GPUs.

ChainerMN: Scalable Distributed Deep Learning Framework

1 code implementation31 Oct 2017 Takuya Akiba, Keisuke Fukuda, Shuji Suzuki

One of the keys for deep learning to have made a breakthrough in various fields was to utilize high computing powers centering around GPUs.

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