Yuma Kinoshita
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuma Kinoshita has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Hitoshi Kiya
Tokyo Metropolitan University rd 6-6 Asahigaoka Hino Tokyo Japan
10 shared publications - Maungmaung Aprilpyone
Information and Society Research Division, National Institute of Informatics (NII), Tokyo 101-8430, Japan
2 shared publications Ayana Kawamura
Tokyo Metropolitan University Tokyo Japan
1 shared publication- Hiroki Ito
Department of Computer Science, Tokyo Metropolitan University, Tokyo, Japan
1 shared publication Hitoshi Kiya
Tokyo Metropolitan University, Tokyo, Japan
1 shared publication- Kouei Yamaoka
Department of Computer Science, Graduate School of Systems Design, Tokyo Metropolitan University, Hino, Tokyo, Japan
1 shared publication
Latest Publications
- Open Access
- 27 September 2024
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2024 (1) , 1-14
End-to-end training of acoustic scene classification using distributed sound-to-light conversion devices: verification through simulation experiments
- 27 September 2024
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2024 (1) , 1-14
Open AccessEnd-to-end training of acoustic scene classification using distributed sound-to-light conversion devices: verification through simulation experiments
- Open Access
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 310-324
Causal and Relaxed-Distortionless Response Beamforming for Online Target Source Extraction
In this paper, we propose a low-latency beamforming method for target source extraction. Beamforming has been performed in the time-frequency domain and achieved promising results in offline applications. Meanwhile, it causes a long algorithmic delay due to the frame analysis. Such a delay is unacceptable in various low-latency real-time applications, including hearing aids. To reduce this delay, we propose a causal variant of the minimum power distortionless response (MPDR) beamformer. The proposed method constraints the non-causal components of the spatial filter to be zero in the optimization of the MPDR beamformer. The algorithmic delay is reduced to zero by applying the causal spatial filter in the time domain. We further propose to relax the distortionless constraint regarding the gain, which allows us to improve the extraction performance without a phase delay. The Douglas–Rachford splitting method and its online extension are adopted to solve the optimization problems of the proposed methods. In our experiment, the relaxed method outperformed various low-latency beamforming methods in terms of extraction performance.
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 310-324
Open AccessCausal and Relaxed-Distortionless Response Beamforming for Online Target Source Extraction
In this paper, we propose a low-latency beamforming method for target source extraction. Beamforming has been performed in the time-frequency domain and achieved promising results in offline applications. Meanwhile, it causes a long algorithmic delay due to the frame analysis. Such a delay is unacceptable in various low-latency real-time applications, including hearing aids. To reduce this delay, we propose a causal variant of the minimum power distortionless response (MPDR) beamformer. The proposed method constraints the non-causal components of the spatial filter to be zero in the optimization of the MPDR beamformer. The algorithmic delay is reduced to zero by applying the causal spatial filter in the time domain. We further propose to relax the distortionless constraint regarding the gain, which allows us to improve the extraction performance without a phase delay. The Douglas–Rachford splitting method and its online extension are adopted to solve the optimization problems of the proposed methods. In our experiment, the relaxed method outperformed various low-latency beamforming methods in terms of extraction performance.
- Open Access
- 19 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 89051-89062
N-White Balancing: White Balancing for Multiple Illuminants Including Non-Uniform Illumination
In this paper, we propose a novel white balance adjustment for multi-illuminant scenes, called “N-white balancing,” in which N source white points are mapped into a ground truth one. Most white balance adjustments focus on adjusting single-illuminant scenes. Several state-of-the-art methods for adjusting multi-illuminant scenes have been proposed, but they need to know the number of segments or the number of light sources in advance. Multi-color balance adjustments have been investigated to improve the performance of white balancing, but they also suffer from color distortion due to the rank deficiency problem. In contrast, the proposed method, N-white balancing, can correct multi-illuminant scenes even when we do not know the exact number of segments or light sources in a scene. In an experiment, the proposed method was demonstrated to outperform state-of-the-art methods under various illumination conditions such as single and multiple illuminants including non-uniform light sources.
- 19 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 89051-89062
Open AccessN-White Balancing: White Balancing for Multiple Illuminants Including Non-Uniform Illumination
In this paper, we propose a novel white balance adjustment for multi-illuminant scenes, called “N-white balancing,” in which N source white points are mapped into a ground truth one. Most white balance adjustments focus on adjusting single-illuminant scenes. Several state-of-the-art methods for adjusting multi-illuminant scenes have been proposed, but they need to know the number of segments or the number of light sources in advance. Multi-color balance adjustments have been investigated to improve the performance of white balancing, but they also suffer from color distortion due to the rank deficiency problem. In contrast, the proposed method, N-white balancing, can correct multi-illuminant scenes even when we do not know the exact number of segments or light sources in a scene. In an experiment, the proposed method was demonstrated to outperform state-of-the-art methods under various illumination conditions such as single and multiple illuminants including non-uniform light sources.
- Open Access
- 22 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 64629-64638
Image to Perturbation: An Image Transformation Network for Generating Visually Protected Images for Privacy-Preserving Deep Neural Networks
We propose a novel image transformation network for generating visually protected images for privacy-preserving deep neural networks (DNNs). The proposed transformation network is trained by using a plain image dataset so that plain images are converted into visually protected ones. Conventional perceptual encryption methods cause some accuracy degradation in image classification and are not robust enough against state-of-the-art attacks. In contrast, the proposed network not only enables us to maintain the image classification accuracy that using plain images achieves but is also strongly robust against attacks including DNN-based ones. Furthermore, there is no need to manage any security keys as the conventional methods require. In an image classification experiment, the proposed network is demonstrated to strongly protect the visual information of plain images while maintaining a high classification accuracy under the use of two typical classification networks: ResNet and VGG. In addition, it is shown that the visually protected images are robust enough against various attacks in an experiment in which we tried to restore the visual information of plain images.
- 22 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 64629-64638
Open AccessImage to Perturbation: An Image Transformation Network for Generating Visually Protected Images for Privacy-Preserving Deep Neural Networks
We propose a novel image transformation network for generating visually protected images for privacy-preserving deep neural networks (DNNs). The proposed transformation network is trained by using a plain image dataset so that plain images are converted into visually protected ones. Conventional perceptual encryption methods cause some accuracy degradation in image classification and are not robust enough against state-of-the-art attacks. In contrast, the proposed network not only enables us to maintain the image classification accuracy that using plain images achieves but is also strongly robust against attacks including DNN-based ones. Furthermore, there is no need to manage any security keys as the conventional methods require. In an image classification experiment, the proposed network is demonstrated to strongly protect the visual information of plain images while maintaining a high classification accuracy under the use of two typical classification networks: ResNet and VGG. In addition, it is shown that the visually protected images are robust enough against various attacks in an experiment in which we tried to restore the visual information of plain images.
- Open Access
Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features
In this paper, we propose a novel convolutional neural network (CNN) that never causes checkerboard artifacts, for image enhancement. In research fields of image-to-image translation problems, it is well-known that images generated by usual CNNs are distorted by checkerboard artifacts which mainly caused in forward-propagation of upsampling layers. However, checkerboard artifacts in image enhancement have never been discussed. In this paper, we point out that applying U-Net based CNNs to image enhancement causes checkerboard artifacts. In contrast, the proposed network that contains fixed convolutional layers can perfectly prevent the artifacts. In addition, the proposed network architecture, which can handle both local and global features, enables us to improve the performance of image enhancement. Experimental results show that the use of fixed convolutional layers can prevent checkerboard artifacts and the proposed network outperforms state-of-the-art CNN-based image-enhancement methods in terms of various objective quality metrics: PSNR, SSIM, and NIQE.
Open AccessCheckerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features
In this paper, we propose a novel convolutional neural network (CNN) that never causes checkerboard artifacts, for image enhancement. In research fields of image-to-image translation problems, it is well-known that images generated by usual CNNs are distorted by checkerboard artifacts which mainly caused in forward-propagation of upsampling layers. However, checkerboard artifacts in image enhancement have never been discussed. In this paper, we point out that applying U-Net based CNNs to image enhancement causes checkerboard artifacts. In contrast, the proposed network that contains fixed convolutional layers can perfectly prevent the artifacts. In addition, the proposed network architecture, which can handle both local and global features, enables us to improve the performance of image enhancement. Experimental results show that the use of fixed convolutional layers can prevent checkerboard artifacts and the proposed network outperforms state-of-the-art CNN-based image-enhancement methods in terms of various objective quality metrics: PSNR, SSIM, and NIQE.
- Open Access
- 8 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 9540-9550
Hue-Correction Scheme Based on Constant-Hue Plane for Deep-Learning-Based Color-Image Enhancement
In this paper, we propose a novel hue-correction scheme based on the constant-hue plane in the RGB color space for deep-learning-based color-image enhancement. Existing hue-preserving image-enhancement methods cannot be applied to state-of-the-art enhancement methods such as deep-learning-based ones. Our main contributions are a discussion on the enhancement performance and the hue distortion of existing image-enhancement methods as well as the first attempt to make hue correction applicable to any existing image-enhancement methods including deep-learning-based ones. This novel scheme is carried out on the basis of the constant-hue plane in the RGB color space. In simulations, we first evaluated conventional image-enhancement methods in terms of the enhancement performance and hue distortion by using five objective metrics: the maximally saturated color similarity, the hue difference in CIEDE2000, discrete entropy, HIGRADE, and NIQMC. The experimental results show that recent deep-learning-based methods have a higher enhancement performance but cause images to be hue-distorted. In addition, the proposed scheme is demonstrated to be effective for suppressing hue distortion even under the use of deep-learning-based enhancement methods. Furthermore, it allows us not only to correct hue but also to maintain the performance of image-enhancement methods.
- 8 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 9540-9550
Open AccessHue-Correction Scheme Based on Constant-Hue Plane for Deep-Learning-Based Color-Image Enhancement
In this paper, we propose a novel hue-correction scheme based on the constant-hue plane in the RGB color space for deep-learning-based color-image enhancement. Existing hue-preserving image-enhancement methods cannot be applied to state-of-the-art enhancement methods such as deep-learning-based ones. Our main contributions are a discussion on the enhancement performance and the hue distortion of existing image-enhancement methods as well as the first attempt to make hue correction applicable to any existing image-enhancement methods including deep-learning-based ones. This novel scheme is carried out on the basis of the constant-hue plane in the RGB color space. In simulations, we first evaluated conventional image-enhancement methods in terms of the enhancement performance and hue distortion by using five objective metrics: the maximally saturated color similarity, the hue difference in CIEDE2000, discrete entropy, HIGRADE, and NIQMC. The experimental results show that recent deep-learning-based methods have a higher enhancement performance but cause images to be hue-distorted. In addition, the proposed scheme is demonstrated to be effective for suppressing hue distortion even under the use of deep-learning-based enhancement methods. Furthermore, it allows us not only to correct hue but also to maintain the performance of image-enhancement methods.
- Open Access
- 12 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177844-177855
Pixel-Based Image Encryption Without Key Management for Privacy-Preserving Deep Neural Networks
We present a novel privacy-preserving scheme for deep neural networks (DNNs) that enables us not to only apply images without visual information to DNNs but to also consider the use of independent encryption keys for both training and testing images for the first time. In this paper, a novel pixel-based image encryption method that maintains important features of original images is proposed for privacy-preserving DNNs. For training, a DNN model is trained with images encrypted by using the proposed method with independent encryption keys. For testing, the model enables us to apply both encrypted images and plain images for image classification. Therefore, there is no need to manage keys. In addition, the proposed method allows us to perform data augmentation in the encrypted domain. In an experiment, the proposed method is applied to well-known networks, that is, deep residual networks and densely connected convolutional networks, for image classification. The experimental results demonstrate that the proposed method, under the use of independent encryption keys, can maintain a high classification performance, and it is robust against ciphertext-only attacks (COAs). Moreover, the results confirm that the proposed scheme is able to classify plain images as well as encrypted images, even when data augmentation is carried out in the encrypted domain.
- 12 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177844-177855
Open AccessPixel-Based Image Encryption Without Key Management for Privacy-Preserving Deep Neural Networks
We present a novel privacy-preserving scheme for deep neural networks (DNNs) that enables us not to only apply images without visual information to DNNs but to also consider the use of independent encryption keys for both training and testing images for the first time. In this paper, a novel pixel-based image encryption method that maintains important features of original images is proposed for privacy-preserving DNNs. For training, a DNN model is trained with images encrypted by using the proposed method with independent encryption keys. For testing, the model enables us to apply both encrypted images and plain images for image classification. Therefore, there is no need to manage keys. In addition, the proposed method allows us to perform data augmentation in the encrypted domain. In an experiment, the proposed method is applied to well-known networks, that is, deep residual networks and densely connected convolutional networks, for image classification. The experimental results demonstrate that the proposed method, under the use of independent encryption keys, can maintain a high classification performance, and it is robust against ciphertext-only attacks (COAs). Moreover, the results confirm that the proposed scheme is able to classify plain images as well as encrypted images, even when data augmentation is carried out in the encrypted domain.
- Open Access
- 9 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177932-177943
Adversarial Robustness by One Bit Double Quantization for Visual Classification
In this paper, we propose a novel robust visual classification framework that uses double quantization (dquant) to defend against adversarial examples in a specific attack scenario called “subsequent adversarial examples” where test images are injected with adversarial noise. The proposed system can remove the adversarial noise completely on this particular attack scenario. First, we analyze the potential sources of adversarial noise and classify adversarial examples into three classes. We then propose a novel effective solution, dquant, to target a specific class of adversarial examples. The first quantization is 1–bit dithering applied to both training and test images. The second one is linear quantization, which is applied to test images just before being inputted to a model to remove any adversarial noise. The linear quantizer guarantees that original 1–bit test images will be restored regardless of adversarial noise distance, and, therefore, dquant maintains identical accuracy whether or not the model is under attack. The results show that dquant achieves comparable accuracy, 85.28% on the CIFAR-10 and 94.99% on the Oxford-IIIT Pet datasets against three state-of-the-art adversaries with even a previously untested maximum adversarial distance of 64.
- 9 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177932-177943
Open AccessAdversarial Robustness by One Bit Double Quantization for Visual Classification
In this paper, we propose a novel robust visual classification framework that uses double quantization (dquant) to defend against adversarial examples in a specific attack scenario called “subsequent adversarial examples” where test images are injected with adversarial noise. The proposed system can remove the adversarial noise completely on this particular attack scenario. First, we analyze the potential sources of adversarial noise and classify adversarial examples into three classes. We then propose a novel effective solution, dquant, to target a specific class of adversarial examples. The first quantization is 1–bit dithering applied to both training and test images. The second one is linear quantization, which is applied to test images just before being inputted to a model to remove any adversarial noise. The linear quantizer guarantees that original 1–bit test images will be restored regardless of adversarial noise distance, and, therefore, dquant maintains identical accuracy whether or not the model is under attack. The results show that dquant achieves comparable accuracy, 85.28% on the CIFAR-10 and 94.99% on the Oxford-IIIT Pet datasets against three state-of-the-art adversaries with even a previously untested maximum adversarial distance of 64.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 802-806
A Hue Correction Scheme Based on Constant-Hue Plane for Color Image Enhancement
In this paper, we propose a novel hue correction scheme based on constant-hue plane in the RGB color space for color image enhancement. A number of hue-preserving image enhancement methods have already been proposed. Although these methods can preserve hue, these methods cannot be applied to the state-of-the-art enhancement methods such as deep-learning based ones. We therefore generalize a hue-preserving method based on the constant-hue plane in this paper. This generalization derives our novel hue correction scheme. In the proposed scheme, any existing image enhancement method including deep-learning based ones can be used to enhance images. The hue distortion due to the enhancement is then removed by replacing the maximally saturated colors of an enhanced image with those of the corresponding input one. Experimental results show that the proposed scheme is effective to suppress the hue distortion due to two color enhancement methods including a deep-learning based one. Furthermore, objective quality evaluations demonstrate that the proposed scheme can maintain the performance of image enhancement methods.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 802-806
A Hue Correction Scheme Based on Constant-Hue Plane for Color Image Enhancement
In this paper, we propose a novel hue correction scheme based on constant-hue plane in the RGB color space for color image enhancement. A number of hue-preserving image enhancement methods have already been proposed. Although these methods can preserve hue, these methods cannot be applied to the state-of-the-art enhancement methods such as deep-learning based ones. We therefore generalize a hue-preserving method based on the constant-hue plane in this paper. This generalization derives our novel hue correction scheme. In the proposed scheme, any existing image enhancement method including deep-learning based ones can be used to enhance images. The hue distortion due to the enhancement is then removed by replacing the maximally saturated colors of an enhanced image with those of the corresponding input one. Experimental results show that the proposed scheme is effective to suppress the hue distortion due to two color enhancement methods including a deep-learning based one. Furthermore, objective quality evaluations demonstrate that the proposed scheme can maintain the performance of image enhancement methods.
- Open Access
Privacy-Preserving Machine Learning Using EtC Images
In this paper, we propose a novel privacy-preserving machine learning scheme with encrypted images, called EtC (Encryption-then-Compression) images. Using machine learning algorithms in cloud environments has been spreading in many fields. However, there are serious issues with it for end users, due to semi-trusted cloud providers. Accordingly, we propose using EtC images, which have been proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is considered under the use of z-score normalization. It is demonstrated that the use of EtC images allows us not only to protect visual information of images, but also to preserve both the Euclidean distance and the inner product between vectors. In addition, dimensionality reduction is shown to can be applied to EtC images for fast and accurate matching. In an experiment, the proposed scheme is applied to a facial recognition algorithm with classifiers for confirming the effectiveness of the scheme under the use of support vector machine (SVM) with the kernel trick.
Open AccessPrivacy-Preserving Machine Learning Using EtC Images
In this paper, we propose a novel privacy-preserving machine learning scheme with encrypted images, called EtC (Encryption-then-Compression) images. Using machine learning algorithms in cloud environments has been spreading in many fields. However, there are serious issues with it for end users, due to semi-trusted cloud providers. Accordingly, we propose using EtC images, which have been proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is considered under the use of z-score normalization. It is demonstrated that the use of EtC images allows us not only to protect visual information of images, but also to preserve both the Euclidean distance and the inner product between vectors. In addition, dimensionality reduction is shown to can be applied to EtC images for fast and accurate matching. In an experiment, the proposed scheme is applied to a facial recognition algorithm with classifiers for confirming the effectiveness of the scheme under the use of support vector machine (SVM) with the kernel trick.