Object detection, which is one of the major research subjects in computer vision, is a basic technology that is critical for autonomous driving and robotics. Challenges in using large-scale datasets, such as ImageNet and MS COCO, to achieve better accuracy in object detection have been the unifying force of the research community, contributing to the rapid improvement of detection techniques and algorithms.

The Google AI Open Images – Object Detection Track held between July 3, 2018 and August 30, 2018 was a competition of an unprecedented scale that used Open Images V4^*2, a large and complex dataset released by Google this year. As a result, the event attracted the attention of many researchers. A total of 454 teams from around the world participated in the competition.

PFN entered the competition as team “PFDet”, comprising interested members, mainly developers of ChainerMN and ChainerCV, PFN’s distributed deep learning library and computer vision library based on deep learning, respectively, as well as specialists in the fields of autonomous driving and robotics. During the competition, PFN’s large-scale cluster MN-1b that has 512 NVIDIA ^(R) Tesla^(R) V100 32GB GPUs was in full operation for the first time since its launch in July this year. In addition, the team utilized a parallel deep learning technique to speed up training with a large-scale dataset and made full use of research results PFN had accumulated over the years in the fields of autonomous driving and robotics.  These efforts resulted in the team finishing in a close second place by a narrow margin of 0.023% behind the team who won first place.

We have published a paper, entitled “PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track,” regarding our solution method in this competition, at https://arxiv.org/abs/1809.00778

We also plan to present the content of the paper at a workshop at the European Conference on Computer Vision （ECCV）2018.

A part of the techniques developed for this competition will be released as additional functionality to ChainerMN and ChainerCV.

• Distributed deep learning framework ChainerMN  https://github.com/chainer/chainermn
• Deep learning-based computer vision library ChainerCV  https://github.com/chainer/chainercv

PFN will continue to work on research and development of image analysis and object detection technologies, and promote their practical applications in our three primary business domains, namely, transportation, manufacturing, and bio/healthcare.

*１：A platform for machine learning competitions

*２：A very large training dataset comprised of 1.7 million images (including 12 million objects of 500 classes)

投稿 Preferred Networks wins second place in the Google AI Open Images – Object Detection Track, competed with 454 teams は Preferred Networks, Inc. に最初に表示されました。

About PFN’s private supercomputer MN-1   ³ 

MN-1 is equipped with a Graphics Processing Unit (GPU) platform from NTT Communications Corporation (NTT Com, Headquarters: Chiyoda-ku, Tokyo, President and CEO: Tetsuya Shoji) and NTT PC Communications Incorporated (NTTPC, Headquarters: Minato-ku, Tokyo, President and CEO: Motoo Tanaka), and contains 1,024 of NVIDIA ^(R) ’s Tesla ^(R) multi-node P100 GPUs. It utilizes Mellanox’s Infiniband interconnect to make high-speed distributed deep learning possible using ChainerMN ⁴, a distributed deep learning package developed by PFN.    

Using MN-1, PFN will further accelerate its research and development activities in various fields that require a huge amount of computing resources such as transportation systems, manufacturing and bio/healthcare.

1.  A benchmark to compare practical operation speed of computers

2.  A unit measuring computer performance. Peta is 1,000 trillion (10 to the power of 15) and FLOPS is used to count floating-point operations per second. So, 1 PetaFLOPS means that a computer is capable of performing 1,000 trillion floating-point calculations per second.

3.  Preferred Networks launches one of Japan’s most powerful private sector supercomputers
https://www.preferred.jp/en/news/pr20170920

4.  Preferred Networks achieved the world’s fastest training time in deep learning
https://www.preferred.jp/en/news/pr20171110

■ About Preferred Networks, Inc.

Founded in March 2014 with the aim of promoting business utilization of deep learning technology focused on IoT, PFN advocates Edge Heavy Computing as a way to handle the enormous amounts of data generated by devices in a distributed and collaborative manner at the edge of the network, driving innovation in three priority business areas: transportation, manufacturing and bio/healthcare. PFN promotes advanced initiatives by collaborating with world leading organizations, such as Toyota Motor Corporation, FANUC CORPORATION, and the National Cancer Center. (https://www.preferred.jp/en/)

＊Chainer ^(R)  is the trademark or the registered trademark of Preferred Networks, Inc. in Japan and other countries. Other company names and product names written in this release are the trademarks or the registered trademarks of each company.

投稿 Preferred Networks’ private supercomputer ranked first in the Japanese industrial supercomputers TOP 500 list は Preferred Networks, Inc. に最初に表示されました。