Arrow Research search

Author name cluster

Satoshi Kurihara

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers
1 author row

Possible papers

12

AAAI Conference 2023 Short Paper

Invertible Conditional GAN Revisited: Photo-to-Manga Face Translation with Modern Architectures (Student Abstract)

  • Taro Hatakeyama
  • Ryusuke Saito
  • Komei Hiruta
  • Atsushi Hashimoto
  • Satoshi Kurihara

Recent style translation methods have extended their transferability from texture to geometry. However, performing translation while preserving image content when there is a significant style difference is still an open problem. To overcome this problem, we propose Invertible Conditional Fast GAN (IcFGAN) based on GAN inversion and cFGAN. It allows for unpaired photo-to-manga face translation. Experimental results show that our method could translate styles under significant style gaps, while the state-of-the-art methods could hardly preserve image content.

PDF Details DOI

AAAI Conference 2019 Short Paper

Semi-Supervised Learning for Electron Microscopy Image Segmentation

  • Eichi Takaya
  • Yusuke Takeichi
  • Mamiko Ozaki
  • Satoshi Kurihara

In the research field called connectomics, it is aimed to investigate the structure and connection of the neural system in the brain and sensory organ of the living things. Earlier studies have been proposed the method to help experts who suffer from labeling for three-dimensional reconstruction, that is important process to observe tiny neuronal structure in detail. In this paper, we proposed semi-supervised learning method, that performs pseudo-labeling. This makes it possible to automatically segment neuronal regions using only a small amount of labeled data. Experimental result showed that our method outperformed normal supervised learning with few labeled samples, while the accuracy was not sufficient yet.

PDF Details

AAMAS Conference 2011 Conference Paper

Evolving Subjective Utilities: Prisoner's Dilemma Game Examples

  • Koichi Moriyama
  • Satoshi Kurihara
  • Masayuki Numao

We have proposed the utility-based Q-learning concept that supposes an agent internally has an emotional mechanism that derives subjective utilities from objective rewards and the agent uses the utilities as rewards of Q-learning. We have also proposed such an emotional mechanism that facilitates cooperative actions in Prisoner's Dilemma (PD) games. However, this mechanism has been designed and implemented manually in order to force the agents to take cooperative actions in PD games. Since it seems slightly unnatural, this work considers whether such an emotional mechanism exists and where it comes from. We try to evolve such mechanisms that facilitate cooperative actions in PD games by conducting simulation experiments with a genetic algorithm, and we investigate the evolved mechanisms from various points of view.

PDF

AAMAS Conference 2008 Conference Paper

Adaptive Manager-side Control Policy in Contract Net Protocol for Massively Multi-Agent Systems

  • Sugawara Toshiharu
  • Satoshi Kurihara
  • Toshio Hirotsu
  • Kensuke Fukuda

We describe a new adaptive manager-side control policy for the contract net protocol for a massively multi-agent system (MMAS). To improve overall performance of MMAS, tasks must be allocated to appropriate agents. From this viewpoint, a number of negotiation protocols were proposed in the MAS context, but most assume a small-scale, unbusy environment. We previously reported that, using contract net protocol (CNP), the overall efficiency could improve by an adequate control of degree of fluctuation in the awarding phase depending on the state of MMAS. In this paper, we propose the method to estimate these states from the bid values, which have hitherto not been used effectively. Then the manager-side policy flexibly and autonomously with some degree of fluctuation responsive to the estimated states is introduced. We also evaluate that our proposed CNP policy.

PDF

AAMAS Conference 2007 Conference Paper

Conflict Estimation of Abstract Plans for Multi-Agent Systems

  • Toshiharu Sugawara
  • Satoshi Kurihara
  • Toshio Hirotsu
  • Kensuke Fukuda
  • Toshihiro Takada

In hierarchical planning, selecting a plan at an abstract level affects planning performance because an abstract plan restricts the scope of primitive plans. However, if all primitive plans under the selected abstract plan have difficult-to-resolve conflicts with the plans of other agents, the final plan after conflict resolution will be inefficient or of low quality. In this paper, we propose a conflict estimation method to generate quality plans efficiently for multi-agent systems by appropriately selecting abstract plans in hierarchical planning. This method enables agents to learn which abstract plans are less likely to cause conflicts or which conflicts will be easy to resolve.

PDF
v2026.09.13