Ryuhei Hamaguchi
National Institute of Advanced Industrial Science and Technology
16 Papers
31 Citations
Ryuhei Hamaguchi is an academic researcher from National Institute of Advanced Industrial Science and Technology. The author has contributed to research in topics: Computer science & Change detection. The author has an hindex of 7, co-authored 13 publications.
Chat about Author
Papers
Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
Ryuhei Hamaguchi,Aito Fujita,Keisuke Nemoto,Tomoyuki Imaizumi,Shuhei Hikosaka +4 more
- 12 Mar 2018
TL;DR: Li et al. as discussed by the authors proposed a novel architecture called Local Feature Extraction (LFE) module attached on top of dilated front-end module, which is based on their findings that aggressively increasing dilation factors fails to aggregate local features due to sparsity of the kernel, and detrimental to small objects.
281
Building Detection from Satellite Imagery using Ensemble of Size-Specific Detectors
Ryuhei Hamaguchi,Shuhei Hikosaka +1 more
- 01 Jun 2018
TL;DR: A simple, but effective multi-task model that learns multiple detectors each of which is dedicated to a specific size of buildings, and implicitly utilizes context information by simultaneously training road extraction task along with building detection task.
Rare Event Detection Using Disentangled Representation Learning
Ryuhei Hamaguchi,Ken Sakurada,Ryosuke Nakamura +2 more
- 01 Jun 2019
TL;DR: In this article, a novel method for rare event detection from an image pair with class-imbalanced datasets is presented. But the method is not suitable for building change detection on satellite images, since few positive samples are available for the training.
Classification of Rare Building Change Using CNN with Multi-Class Focal Loss
Keisuke Nemoto,Ryuhei Hamaguchi,Tomoyuki Imaizumi,Shuhei Hikosaka +3 more
- 22 Jul 2018
TL;DR: From the experimental results, not only the class imbalance but also the overfitting is affected the down-weighting effect of the focal loss, which automatically adjusts learning speed for each class.
26
•Posted Content
Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
TL;DR: A novel architecture called local feature extraction (LFE) module attached on top of dilated front-end module is proposed based on the findings that aggressively increasing dilation factors fails to aggregate local features due to sparsity of the kernel, and detrimental to small objects.
16