Preferred Infrastructure

research

∙ 12/09/2019

ChainerRL: A Deep Reinforcement Learning Library

In this paper, we introduce ChainerRL, an open-source Deep Reinforcement...

Yasuhiro Fujita, et al. ∙

research

∙ 06/22/2020

Differentiable Rendering: A Survey

Deep neural networks (DNNs) have shown remarkable performance improvemen...

Hiroharu Kato, et al. ∙

research

∙ 06/01/2022

On Layer Normalizations and Residual Connections in Transformers

In the perspective of a layer normalization (LN) position, the architect...

Sho Takase, et al. ∙

research

∙ 02/04/2019

Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks

Recently, Graph Neural Networks (GNNs) are trending in the machine learn...

Katsuhiko Ishiguro, et al. ∙

research

∙ 05/24/2022

Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model

Ensembling is a popular method used to improve performance as a last res...

Sosuke Kobayashi, et al. ∙

research

∙ 01/05/2022

Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis

We propose a new method for reconstructing controllable implicit 3D huma...

Tianhan Xu, et al. ∙

research

∙ 09/13/2021

SHAPE: Shifted Absolute Position Embedding for Transformers

Position representation is crucial for building position-aware represent...

Shun Kiyono, et al. ∙

research

∙ 03/25/2020

Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval

We propose an efficient pipeline for large-scale landmark image retrieva...

Shuhei Yokoo, et al. ∙

research

∙ 11/24/2020

Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation

Automated Vehicles require exhaustive testing in simulation to detect as...

Daisuke Nishiyama, et al. ∙

research

∙ 06/08/2021

Hierarchical Lovász Embeddings for Proposal-free Panoptic Segmentation

Panoptic segmentation brings together two separate tasks: instance and s...

Tommi Kerola, et al. ∙

research

∙ 09/20/2019

Reconnaissance and Planning algorithm for constrained MDP

Practical reinforcement learning problems are often formulated as constr...

Shin-ichi Maeda, et al. ∙

research

∙ 12/09/2019

Learning Latent State Spaces for Planning through Reward Prediction

Model-based reinforcement learning methods typically learn models for hi...

Aaron Havens, et al. ∙

research

∙ 04/17/2020

Fast Soft Color Segmentation

We address the problem of soft color segmentation, defined as decomposin...

Naofumi Akimoto, et al. ∙

research

∙ 05/31/2022

Decomposing NeRF for Editing via Feature Field Distillation

Emerging neural radiance fields (NeRF) are a promising scene representat...

Sosuke Kobayashi, et al. ∙

research

∙ 11/16/2017

Superpixel clustering with deep features for unsupervised road segmentation

Vision-based autonomous driving requires classifying each pixel as corre...

Shunta Saito, et al. ∙

research

∙ 02/01/2020

Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning

Off-policy ensemble reinforcement learning (RL) methods have demonstrate...

Zhang-Wei Hong, et al. ∙

research

∙ 10/31/2017

ChainerMN: Scalable Distributed Deep Learning Framework

One of the keys for deep learning to have made a breakthrough in various...

Takuya Akiba, et al. ∙

research

∙ 11/28/2017

Semi-supervised learning of hierarchical representations of molecules using neural message passing

With the rapid increase of compound databases available in medicinal and...

Hai Nguyen, et al. ∙

research

∙ 10/17/2017

Map-based Multi-Policy Reinforcement Learning: Enhancing Adaptability of Robots by Deep Reinforcement Learning

In order for robots to perform mission-critical tasks, it is essential t...

Ayaka Kume, et al. ∙

research

∙ 11/20/2017

Parameter Reference Loss for Unsupervised Domain Adaptation

The success of deep learning in computer vision is mainly attributed to ...

Jiren Jin, et al. ∙

research

∙ 11/12/2017

Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes

We demonstrate that training ResNet-50 on ImageNet for 90 epochs can be ...

Takuya Akiba, et al. ∙

research

∙ 08/28/2017

ChainerCV: a Library for Deep Learning in Computer Vision

Despite significant progress of deep learning in the field of computer v...

Yusuke Niitani, et al. ∙

research

∙ 05/31/2017

Spectral Norm Regularization for Improving the Generalizability of Deep Learning

We investigate the generalizability of deep learning based on the sensit...

Yuichi Yoshida, et al. ∙

research

∙ 11/04/2016

Reparameterization trick for discrete variables

Low-variance gradient estimation is crucial for learning directed graphi...

Seiya Tokui, et al. ∙

research

∙ 11/21/2016

Temporal Generative Adversarial Nets with Singular Value Clipping

In this paper, we propose a generative model, Temporal Generative Advers...

Masaki Saito, et al. ∙

research

∙ 10/17/2017

Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions

Comprehension of spoken natural language is an essential component for r...

Jun Hatori, et al. ∙

research

∙ 09/06/2017

A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse

This study addresses the problem of identifying the meaning of unknown w...

Sosuke Kobayashi, et al. ∙

research

∙ 02/15/2018

cGANs with Projection Discriminator

We propose a novel, projection based way to incorporate the conditional ...

Takeru Miyato, et al. ∙

research

∙ 02/16/2018

Variance-based Gradient Compression for Efficient Distributed Deep Learning

Due to the substantial computational cost, training state-of-the-art dee...

Yusuke Tsuzuku, et al. ∙

research

∙ 02/16/2018

Spectral Normalization for Generative Adversarial Networks

One of the challenges in the study of generative adversarial networks is...

Takeru Miyato, et al. ∙

research

∙ 03/09/2018

Deep Visuo-Tactile Learning: Estimation of Material Properties from Images

Estimation of materials properties, such as softness or roughness from v...

Kuniyuki Takahashi, et al. ∙

research

∙ 05/08/2018

Interpretable Adversarial Perturbation in Input Embedding Space for Text

Following great success in the image processing field, the idea of adver...

Motoki Sato, et al. ∙

research

∙ 05/15/2018

Unsupervised Learning of Style-sensitive Word Vectors

This paper presents the first study aimed at capturing stylistic similar...

Reina Akama, et al. ∙

research

∙ 05/16/2018

Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations

We propose a novel data augmentation for labeled sentences called contex...

Sosuke Kobayashi, et al. ∙

research

∙ 07/04/2018

BayesGrad: Explaining Predictions of Graph Convolutional Networks

Recent advances in graph convolutional networks have significantly impro...

Hirotaka Akita, et al. ∙

research

∙ 08/12/2018

Addressee and Response Selection for Multilingual Conversation

Developing conversational systems that can converse in many languages is...

Motoki Sato, et al. ∙

research

∙ 09/04/2018

Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions

In this paper, we propose a new kernel-based co-occurrence measure that ...

Sho Yokoi, et al. ∙

research

∙ 09/04/2018

PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track

We present a large-scale object detection system by team PFDet. Our syst...

Takuya Akiba, et al. ∙

research

∙ 09/15/2018

Deterministic Implementations for Reproducibility in Deep Reinforcement Learning

While deep reinforcement learning (DRL) has led to numerous successes in...

prabhatn, et al. ∙

research

∙ 10/28/2018

DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback

Exploration has been one of the greatest challenges in reinforcement lea...

Riku Arakawa, et al. ∙

research

∙ 11/02/2018

Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning

The problem-solving in automated theorem proving (ATP) can be interprete...

Mitsuru Kusumoto, et al. ∙

research

∙ 11/22/2018

TGANv2: Efficient Training of Large Models for Video Generation with Multiple Subsampling Layers

In this paper, we propose a novel method to efficiently train a Generati...

Masaki Saito, et al. ∙

research

∙ 11/27/2018

Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects

Efficient and reliable methods for training of object detectors are in h...

Yusuke Niitani, et al. ∙

research

∙ 01/29/2019

Dynamic Manipulation of Flexible Objects with Torque Sequence Using a Deep Neural Network

For dynamic manipulation of flexible objects, we propose an acquisition ...

Kento Kawaharazuka, et al. ∙

research

∙ 02/05/2019

Low-latency job scheduling with preemption for the development of deep learning

One significant challenge in the job scheduling of computing clusters fo...

Hidehito Yabuuchi, et al. ∙

research

∙ 05/28/2019

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

Recomputation algorithms collectively refer to a family of methods that ...

Mitsuru Kusumoto, et al. ∙

research

∙ 05/24/2019

Robustness to Adversarial Perturbations in Learning from Incomplete Data

What is the role of unlabeled data in an inference problem, when the pre...

Amir Najafi, et al. ∙

research

∙ 08/01/2019

Chainer: A Deep Learning Framework for Accelerating the Research Cycle

Software frameworks for neural networks play a key role in the developme...

Seiya Tokui, et al. ∙

research

∙ 09/10/2019

FDA: Feature Disruptive Attack

Though Deep Neural Networks (DNN) show excellent performance across vari...

Aditya Ganeshan, et al. ∙

research

∙ 09/27/2019

GA-GAN: CT reconstruction from Biplanar DRRs using GAN with Guided Attention

This work investigates the use of guided attention in the reconstruction...

Ashish Sinha, et al. ∙

Preferred Infrastructure

Featured Researchers