no code implementations • 13 Mar 2024 • Yusuke Marumo, Kazuhiko Kawamoto, Hiroshi Kera
Not identical but similar objects are everywhere in the world.
1 code implementation • 16 Feb 2024 • Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
In this study, we provide a theoretical framework for understanding learning from perturbations using a one-hidden-layer network trained on mutually orthogonal samples.
1 code implementation • 8 Jan 2024 • Kosuke Sumiyasu, Kazuhiko Kawamoto, Hiroshi Kera
To better understand the behavior of image classifiers, it is useful to visualize the contribution of individual pixels to the model prediction.
no code implementations • 21 Nov 2023 • Hiroshi Kera, Yuki Ishihara, Yuta Kambe, Tristan Vaccon, Kazuhiro Yokoyama
Solving a polynomial system, or computing an associated Gr\"obner basis, has been a fundamental task in computational algebra.
1 code implementation • 29 May 2023 • Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto
Using Fourier analysis, we explore the robustness and vulnerability of graph convolutional neural networks (GCNs) for skeleton-based action recognition.
no code implementations • 15 May 2023 • Chun Yang Tan, Kazuhiko Kawamoto, Hiroshi Kera
In recent years, there has been growing concern over the vulnerability of convolutional neural networks (CNNs) to image perturbations.
no code implementations • 21 Jan 2023 • Nan Wu, Hiroshi Kera, Kazuhiko Kawamoto
Furthermore, the proposed model can also be combined with other models to improve its accuracy.
no code implementations • 27 Oct 2022 • Ryosuke Masuya, Yuichi Ike, Hiroshi Kera
Vanishing component analysis (VCA) computes approximate generators of vanishing ideals of samples, which are further used for extracting nonlinear features of the samples.
no code implementations • 7 Oct 2022 • Kosuke Sumiyasu, Kazuhiko Kawamoto, Hiroshi Kera
This paper analyzes various types of image misclassification from a game-theoretic view.
1 code implementation • 4 Jul 2022 • Elias Wirth, Hiroshi Kera, Sebastian Pokutta
The vanishing ideal of a set of points $X = \{\mathbf{x}_1, \ldots, \mathbf{x}_m\}\subseteq \mathbb{R}^n$ is the set of polynomials that evaluate to $0$ over all points $\mathbf{x} \in X$ and admits an efficient representation by a finite subset of generators.
no code implementations • 29 May 2022 • Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken.
no code implementations • 20 May 2022 • Takuto Otomo, Hiroshi Kera, Kazuhiko Kawamoto
In experiments with the quadruped robot Ant-v2 and the bipedal robot Humanoid-v2, in OpenAI Gym environments, we find that differential evolution can efficiently find the strongest torque perturbations among the three methods.
no code implementations • 20 May 2022 • Takaaki Azakami, Hiroshi Kera, Kazuhiko Kawamoto
We propose an evolutionary computation method for an adversarial attack on the length and thickness of parts of legged robots by deep reinforcement learning.
no code implementations • 14 Mar 2022 • Chun Yang Tan, Kazuhiko Kawamoto, Hiroshi Kera
Extensive experiments revealed that the images generated by combining the amplitude spectrum of adversarial images and the phase spectrum of clean images accommodates moderate and general perturbations, and training with these images equips a CNN classifier with more general robustness, performing well under both common corruptions and adversarial perturbations.
no code implementations • 19 Nov 2021 • Wataru Okamoto, Hiroshi Kera, Kazuhiko Kawamoto
This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments.
no code implementations • 13 Sep 2021 • Kazuma Fujii, Hiroshi Kera, Kazuhiko Kawamoto
In addition, we propose a method that combines adversarial training and feature alignment to ensure the improved alignment of robust features with the target domain.
no code implementations • 13 Sep 2021 • Nariki Tanaka, Hiroshi Kera, Kazuhiko Kawamoto
Specifically, we restrict the perturbations to the lengths of the skeleton's bones, which allows an adversary to manipulate only approximately 30 effective dimensions.
no code implementations • 13 Sep 2021 • Kevin Richard G. Operiano, Wanchalerm Pora, Hitoshi Iba, Hiroshi Kera
Deep neural network image classifiers are known to be susceptible not only to adversarial examples created for them but even those created for others.
no code implementations • 2 Jan 2021 • Hiroshi Kera
This study proposes the gradient-weighted normalization method for the approximate border basis computation of vanishing ideals, inspired by recent developments in machine learning.
1 code implementation • 7 Dec 2020 • Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
In this paper, we address the question of whether there can be fooling images with no characteristic pattern of natural objects locally or globally.
no code implementations • 11 Nov 2019 • Hiroshi Kera, Yoshihiko Hasegawa
In the last decade, the approximate vanishing ideal and its basis construction algorithms have been extensively studied in computer algebra and machine learning as a general model to reconstruct the algebraic variety on which noisy data approximately lie.
no code implementations • 25 Jan 2019 • Hiroshi Kera, Yoshihiko Hasegawa
We further propose a method that takes advantage of the iterative nature of basis construction so that computationally costly operations for coefficient normalization can be circumvented.
no code implementations • 29 Jan 2018 • Hiroshi Kera, Yoshihiko Hasegawa
The present paper proposes a vanishing ideal that is tolerant to noisy data and also pursued to have a better algebraic structure.