Search Results for author: Toshiki Nakamura

Found 5 papers, 2 papers with code

MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts due to Changes in Operational and Environmental Conditions

5 code implementations6 May 2021 Ryo Tanabe, Harsh Purohit, Kota Dohi, Takashi Endo, Yuki Nikaido, Toshiki Nakamura, Yohei Kawaguchi

In this paper, we introduce MIMII DUE, a new dataset for malfunctioning industrial machine investigation and inspection with domain shifts due to changes in operational and environmental conditions.

Task 2

n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization

no code implementations22 Mar 2021 Yuiko Sakuma, Hiroshi Sumihiro, Jun Nishikawa, Toshiki Nakamura, Ryoji Ikegaya

Moreover, we use a two-stage fine-tuning algorithm to recover the accuracy drop that is triggered by introducing the bit-level sparsity.

object-detection Object Detection +1

Scene Text Magnifier

no code implementations17 Jun 2019 Toshiki Nakamura, Anna Zhu, Seiichi Uchida

In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, character magnify, and image synthesis.

Image Generation text annotation

Scene Text Eraser

no code implementations8 May 2017 Toshiki Nakamura, Anna Zhu, Keiji Yanai, Seiichi Uchida

That proves the effectiveness of proposed method for erasing the text in natural scene images.

Scene Text Detection Text Detection

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