no code implementations • 27 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.
1 code implementation • 11 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.
no code implementations • 12 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
no code implementations • 8 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.