◍wovepaper
SearchResearchersInstitutions
Sign in
institution

Denso IT Laboratory Inc. (Japan)

Japan

3 papers here11 citations across 3
fields
  • cs.CV2
  • cs.LG1
ROR 05hv2ye71OpenAlex

affiliations via OpenAlex

most citedLossy compression of matrices by black-box optimisation of mixed integer nonlinear programming

10 citations

researchers with a paper here
  • Teppei Suzuki2 · h 8
  • Keisuke Ozawa1 · h 4
  • Mitsuru Ambai1 · h 7
  • T. Kadowaki1 · h 11
  • Yusuke Sekikawa1 · h 8
collaborating institutions
  • Denso (United States)US2 papers
  • National Institute of Advanced Industrial Science and TechnologyJP1 paper
  • Shibuya (Japan)JP1 paper

3 papers

cs.LG2022★ 10 cited

Lossy compression of matrices by black-box optimisation of mixed integer nonlinear programming

Tadashi Kadowaki, Mitsuru Ambai

In edge computing, suppressing data size is a challenge for machine learning models that perform complex tasks such as autonomous driving, in which computational resources (speed,…

cs.CV2020

Rethinking PointNet Embedding for Faster and Compact Model

Teppei Suzuki, Keisuke Ozawa, Yusuke Sekikawa

PointNet, which is the widely used point-wise embedding method and known as a universal approximator for continuous set functions, can process one million points per second. Nevert…

cs.CV2020★ 1 cited

Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization

Teppei Suzuki

We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time. Our method generates superpixel…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.