Search Results for author: Tomoyoshi Takebayashi

Found 4 papers, 1 papers with code

Crowdsourcing Evaluation of Saliency-based XAI Methods

no code implementations27 Jun 2021 Xiaotian Lu, Arseny Tolmachev, Tatsuya Yamamoto, Koh Takeuchi, Seiji Okajima, Tomoyoshi Takebayashi, Koji Maruhashi, Hisashi Kashima

In order to compare various saliency-based XAI methods quantitatively, several approaches for automated evaluation schemes have been proposed; however, there is no guarantee that such automated evaluation metrics correctly evaluate explainability, and a high rating by an automated evaluation scheme does not necessarily mean a high explainability for humans.

Explainable Artificial Intelligence (XAI)

Inter-domain Multi-relational Link Prediction

1 code implementation11 Jun 2021 Luu Huu Phuc, Koh Takeuchi, Seiji Okajima, Arseny Tolmachev, Tomoyoshi Takebayashi, Koji Maruhashi, Hisashi Kashima

Multi-relational graph is a ubiquitous and important data structure, allowing flexible representation of multiple types of interactions and relations between entities.

Link Prediction

A Multi-task Learning Framework for Grasping-Position Detection and Few-Shot Classification

no code implementations12 Mar 2020 Yasuto Yokota, Kanata Suzuki, Yuzi Kanazawa, Tomoyoshi Takebayashi

However, the DNN that was used to detect grasping positions has two problems with respect to extracting feature vectors from a layer for shape classification: (1) Because each layer of the grasping position detection DNN is activated by all objects in the input image, it is necessary to refine the features for each grasping position.

Robotics

Online Self-Supervised Learning for Object Picking: Detecting Optimum Grasping Position using a Metric Learning Approach

no code implementations8 Mar 2020 Kanata Suzuki, Yasuto Yokota, Yuzi Kanazawa, Tomoyoshi Takebayashi

: SSD that detects the grasping position of an object, and Siamese networks (SNs) that evaluate the trial sample using the similarity of two input data in the feature space.

Metric Learning Object +2

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