Search Results for author: Tsubasa Hirakawa

Found 19 papers, 3 papers with code

Learning from AI: An Interactive Learning Method Using a DNN Model Incorporating Expert Knowledge as a Teacher

no code implementations4 Jun 2023 Kohei Hattori, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

In this study, based on a deep-learning model that incorporates the knowledge of experts, a method by which a learner "learns from AI" the grounds for its decisions is proposed.

Decision Making

Masking and Mixing Adversarial Training

no code implementations16 Feb 2023 Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Yasunori Ishii, Kazuki Kozuka

Adversarial training is a popular and straightforward technique to defend against the threat of adversarial examples.

Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition

no code implementations27 Jul 2022 Tomoya Nitta, Tsubasa Hirakawa, Hironobu Fujiyoshi, Toru Tamaki

Experimental results with UCF101 and SSv2 shows that the generated maps by the proposed method are much clearer qualitatively and quantitatively than those of the original ABN.

Action Recognition Instance Segmentation +2

Deep Ensemble Collaborative Learning by using Knowledge-transfer Graph for Fine-grained Object Classification

no code implementations27 Mar 2021 Naoki Okamoto, Soma Minami, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

In this study, we propose an ensemble method using knowledge transfer to improve the accuracy of ensembles by introducing a loss design that promotes diversity among networks in mutual learning.

Ensemble Learning General Classification +2

Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning

no code implementations6 Mar 2021 Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Komei Sugiura

A3C consists of a feature extractor that extracts features from an image, a policy branch that outputs the policy, and a value branch that outputs the state value.

Decision Making reinforcement-learning +1

Improved Activity Forecasting for Generating Trajectories

no code implementations12 Dec 2019 Daisuke Ogawa, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Ken Yoda

An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting.

reinforcement-learning Reinforcement Learning (RL)

Knowledge Transfer Graph for Deep Collaborative Learning

1 code implementation10 Sep 2019 Soma Minami, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

To achieve the knowledge transfer, we propose a novel graph representation called knowledge transfer graph that provides a unified view of the knowledge transfer and has the potential to represent diverse knowledge transfer patterns.

Knowledge Distillation Transfer Learning

Attention Branch Network: Learning of Attention Mechanism for Visual Explanation

3 code implementations CVPR 2019 Hiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

ABN can be applicable to several image recognition tasks by introducing a branch for attention mechanism and is trainable for the visual explanation and image recognition in end-to-end manner.

Decision Making Image Classification

Survey on Vision-based Path Prediction

no code implementations1 Nov 2018 Tsubasa Hirakawa, Takayoshi Yamashita, Toru Tamaki, Hironobu Fujiyoshi

Because path prediction as a task of computer vision uses video as input, various information used for prediction, such as the environment surrounding the target and the internal state of the target, need to be estimated from the video in addition to predicting paths.

Development of a Real-time Colorectal Tumor Classification System for Narrow-band Imaging zoom-videoendoscopy

no code implementations15 Dec 2016 Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka

A computer-aided diagnosis (CAD) system that provides an objective measure to endoscopists during colorectal endoscopic examinations would be of great value.

General Classification

Domain Adaptation with L2 constraints for classifying images from different endoscope systems

no code implementations8 Nov 2016 Toru Tamaki, Shoji Sonoyama, Takio Kurita, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka, Kazuaki Chayama

This paper proposes a method for domain adaptation that extends the maximum margin domain transfer (MMDT) proposed by Hoffman et al., by introducing L2 distance constraints between samples of different domains; thus, our method is denoted as MMDTL2.

Domain Adaptation

Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features

no code implementations24 Aug 2016 Toru Tamaki, Shoji Sonoyama, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka

In this paper we report results for recognizing colorectal NBI endoscopic images by using features extracted from convolutional neural network (CNN).

General Classification

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