Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization

no code implementations • 10 Dec 2020 • Guillaume Le Moing, Don Joven Agravante, Tadanobu Inoue, Jayakorn Vongkulbhisal, Asim Munawar, Ryuki Tachibana, Phongtharin Vinayavekhin

This paper introduces an ensemble of discriminators that improves the accuracy of a domain adaptation technique for the localization of multiple sound sources.

Domain Adaptation

Data-Efficient Framework for Real-world Multiple Sound Source 2D Localization

no code implementations • 10 Dec 2020 • Guillaume Le Moing, Phongtharin Vinayavekhin, Don Joven Agravante, Tadanobu Inoue, Jayakorn Vongkulbhisal, Asim Munawar, Ryuki Tachibana

Moreover, learning for different microphone array layouts makes the task more complicated due to the infinite number of possible layouts.

Learning Multiple Sound Source 2D Localization

no code implementations • 10 Dec 2020 • Guillaume Le Moing, Phongtharin Vinayavekhin, Tadanobu Inoue, Jayakorn Vongkulbhisal, Asim Munawar, Ryuki Tachibana, Don Joven Agravante

In this paper, we propose novel deep learning based algorithms for multiple sound source localization.

Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection

no code implementations • 4 Jul 2018 • Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data.

Position Transfer Learning

Model-based imitation learning from state trajectories

no code implementations • ICLR 2018 • Subhajit Chaudhury, Daiki Kimura, Tadanobu Inoue, Ryuki Tachibana

We present a model-based imitation learning method that can learn environment-specific optimal actions only from expert state trajectories.

Imitation Learning reinforcement-learning +1

Transfer learning from synthetic to real images using variational autoencoders for robotic applications

no code implementations • 20 Sep 2017 • Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta

It detects object positions 6 to 7 times more precisely than the baseline of directly learning from the dataset of the real images.

Object Position +1

Deep Reinforcement Learning for High Precision Assembly Tasks

no code implementations • 14 Aug 2017 • Tadanobu Inoue, Giovanni De Magistris, Asim Munawar, Tsuyoshi Yokoya, Ryuki Tachibana

High precision assembly of mechanical parts requires accuracy exceeding the robot precision.

Position reinforcement-learning +2