Akira TANAKA Masanari NAKAMURA Hideyuki IMAI
The solution of the ordinary kernel ridge regression, based on the squared loss function and the squared norm-based regularizer, can be easily interpreted as a stochastic linear estimator by considering the autocorrelation prior for an unknown true function. As is well known, a stochastic affine estimator is one of the simplest extensions of the stochastic linear estimator. However, its corresponding kernel regression problem is not revealed so far. In this paper, we give a formulation of the kernel regression problem, whose solution is reduced to a stochastic affine estimator, and also give interpretations of the formulation.
Kenshiro TAMATA Tomohiro MASHITA
A typical approach to reconstructing a 3D environment model is scanning the environment with a depth sensor and fitting the accumulated point cloud to 3D models. In this kind of scenario, a general 3D environment reconstruction application assumes temporally continuous scanning. However in some practical uses, this assumption is unacceptable. Thus, a point cloud matching method for stitching several non-continuous 3D scans is required. Point cloud matching often includes errors in the feature point detection because a point cloud is basically a sparse sampling of the real environment, and it may include quantization errors that cannot be ignored. Moreover, depth sensors tend to have errors due to the reflective properties of the observed surface. We therefore make the assumption that feature point pairs between two point clouds will include errors. In this work, we propose a feature description method robust to the feature point registration error described above. To achieve this goal, we designed a deep learning based feature description model that consists of a local feature description around the feature points and a global feature description of the entire point cloud. To obtain a feature description robust to feature point registration error, we input feature point pairs with errors and train the models with metric learning. Experimental results show that our feature description model can correctly estimate whether the feature point pair is close enough to be considered a match or not even when the feature point registration errors are large, and our model can estimate with higher accuracy in comparison to methods such as FPFH or 3DMatch. In addition, we conducted experiments for combinations of input point clouds, including local or global point clouds, both types of point cloud, and encoders.
Local discriminative regions play important roles in fine-grained image analysis tasks. How to locate local discriminative regions with only category label and learn discriminative representation from these regions have been hot spots. In our work, we propose Searching Discriminative Regions (SDR) and Learning Discriminative Regions (LDR) method to search and learn local discriminative regions in images. The SDR method adopts attention mechanism to iteratively search for high-response regions in images, and uses this as a clue to locate local discriminative regions. Moreover, the LDR method is proposed to learn compact within category and sparse between categories representation from the raw image and local images. Experimental results show that our proposed approach achieves excellent performance in both fine-grained image retrieval and classification tasks, which demonstrates its effectiveness.
Naohiro TAWARA Atsunori OGAWA Tomoharu IWATA Hiroto ASHIKAWA Tetsunori KOBAYASHI Tetsuji OGAWA
Most conventional multi-source domain adaptation techniques for recurrent neural network language models (RNNLMs) are domain-centric. In these approaches, each domain is considered independently and this makes it difficult to apply the models to completely unseen target domains that are unobservable during training. Instead, our study exploits domain attributes, which represent common knowledge among such different domains as dialects, types of wordings, styles, and topics, to achieve domain generalization that can robustly represent unseen target domains by combining the domain attributes. To achieve attribute-based domain generalization system in language modeling, we introduce domain attribute-based experts to a multi-stream RNNLM called recurrent adaptive mixture model (RADMM) instead of domain-based experts. In the proposed system, a long short-term memory is independently trained on each domain attribute as an expert model. Then by integrating the outputs from all the experts in response to the context-dependent weight of the domain attributes of the current input, we predict the subsequent words in the unseen target domain and exploit the specific knowledge of each domain attribute. To demonstrate the effectiveness of our proposed domain attributes-centric language model, we experimentally compared the proposed model with conventional domain-centric language model by using texts taken from multiple domains including different writing styles, topics, dialects, and types of wordings. The experimental results demonstrated that lower perplexity can be achieved using domain attributes.
Zihao SONG Peng SONG Chao SHENG Wenming ZHENG Wenjing ZHANG Shaokai LI
Unsupervised Feature selection is an important dimensionality reduction technique to cope with high-dimensional data. It does not require prior label information, and has recently attracted much attention. However, it cannot fully utilize the discriminative information of samples, which may affect the feature selection performance. To tackle this problem, in this letter, we propose a novel discriminative virtual label regression method (DVLR) for unsupervised feature selection. In DVLR, we develop a virtual label regression function to guide the subspace learning based feature selection, which can select more discriminative features. Moreover, a linear discriminant analysis (LDA) term is used to make the model be more discriminative. To further make the model be more robust and select more representative features, we impose the ℓ2,1-norm on the regression and feature selection terms. Finally, extensive experiments are carried out on several public datasets, and the results demonstrate that our proposed DVLR achieves better performance than several state-of-the-art unsupervised feature selection methods.
Bodin CHINTHANET Raula GAIKOVINA KULA Rodrigo ELIZA ZAPATA Takashi ISHIO Kenichi MATSUMOTO Akinori IHARA
It has become common practice for software projects to adopt third-party dependencies. Developers are encouraged to update any outdated dependency to remain safe from potential threats of vulnerabilities. In this study, we present an approach to aid developers show whether or not a vulnerable code is reachable for JavaScript projects. Our prototype, SōjiTantei, is evaluated in two ways (i) the accuracy when compared to a manual approach and (ii) a larger-scale analysis of 780 clients from 78 security vulnerability cases. The first evaluation shows that SōjiTantei has a high accuracy of 83.3%, with a speed of less than a second analysis per client. The second evaluation reveals that 68 out of the studied 78 vulnerabilities reported having at least one clean client. The study proves that automation is promising with the potential for further improvement.
Huy H. NGUYEN Minoru KURIBAYASHI Junichi YAMAGISHI Isao ECHIZEN
Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks in which noise is added to the input to change the networks' output. Consequently, DNN-based mission-critical applications such as those used in self-driving vehicles have reduced reliability and could cause severe accidents and damage. Moreover, adversarial examples could be used to poison DNN training data, resulting in corruptions of trained models. Besides the need for detecting adversarial examples, correcting them is important for restoring data and system functionality to normal. We have developed methods for detecting and correcting adversarial images that use multiple image processing operations with multiple parameter values. For detection, we devised a statistical-based method that outperforms the feature squeezing method. For correction, we devised a method that uses for the first time two levels of correction. The first level is label correction, with the focus on restoring the adversarial images' original predicted labels (for use in the current task). The second level is image correction, with the focus on both the correctness and quality of the corrected images (for use in the current and other tasks). Our experiments demonstrated that the correction method could correct nearly 90% of the adversarial images created by classical adversarial attacks and affected only about 2% of the normal images.
Jiayi LI Lin YANG Junyan YI Haichuan YANG Yuki TODO Shangce GAO
Differential Evolution (DE) algorithm is simple and effective. Since DE has been proposed, it has been widely used to solve various complex optimization problems. To further exploit the advantages of DE, we propose a new variant of DE, termed as ranking-based differential evolution (RDE), by performing ranking on the population. Progressively better individuals in the population are used for mutation operation, thus improving the algorithm's exploitation and exploration capability. Experimental results on a number of benchmark optimization functions show that RDE significantly outperforms the original DE and performs competitively in comparison with other two state-of-the-art DE variants.
Yushi TAMENORI Haruka TOKUNAGA Li YI Tadao NAGATSUMA
The demand for non-destructive inspection of the thermal insulation layer of Japanese houses has been increasing. Surface temperature measurement is commonly used for estimating the condition of the thermal insulation layer that is located inside the walls. However, the accuracy needs to be improved because this approach only considers the surface information. To evaluate the thermal insulation layer inside the walls, a millimeter-wave tomography system is proposed for measuring the water content. The system can provide ∼10 mm range resolution to differentiate the reflections from the thermal insulation layer behind the external wall. The Lichtenecker-Rother model is applied for the quantitative evaluation of the water content using the reflected signal. The proposed model is consistent with the experimental data, confirming that a maximum error of 16.0% is obtained. It is also demonstrated that the water content distribution can be visualized with a range resolution of 10.6 mm.
Reona TAKEMOTO Takayuki NOZAKI
Maximum run-length limited codes are constraint codes used in communication and data storage systems. Insertion/deletion correcting codes correct insertion or deletion errors caused in transmitted sequences and are used for combating synchronization errors. This paper investigates the maximum run-length limited single insertion/deletion correcting (RLL-SIDC) codes. More precisely, we construct efficiently encodable and decodable RLL-SIDC codes. Moreover, we present its encoding and decoding algorithms and show the redundancy of the code.
Expectation propagation (EP) is a powerful algorithm for signal recovery in compressed sensing. This letter proposes correction of a variance message before denoising to improve the performance of EP in the high signal-to-noise ratio (SNR) regime for finite-sized systems. The variance massage is replaced by an observation-dependent consistent estimator of the mean-square error in estimation before denoising. Massive multiple-input multiple-output (MIMO) is considered to verify the effectiveness of the proposed correction. Numerical simulations show that the proposed variance correction improves the high SNR performance of EP for massive MIMO with a few hundred transmit and receive antennas.
This paper introduces our work on a Movie Map, which will enable users to explore a given city area using 360° videos. Visual exploration of a city is always needed. Nowadays, we are familiar with Google Street View (GSV) that is an interactive visual map. Despite the wide use of GSV, it provides sparse images of streets, which often confuses users and lowers user satisfaction. Forty years ago, a video-based interactive map was created - it is well-known as Aspen Movie Map. Movie Map uses videos instead of sparse images and seems to improve the user experience dramatically. However, Aspen Movie Map was based on analog technology with a huge effort and never built again. Thus, we renovate the Movie Map using state-of-the-art technology. We build a new Movie Map system with an interface for exploring cities. The system consists of four stages; acquisition, analysis, management, and interaction. After acquiring 360° videos along streets in target areas, the analysis of videos is almost automatic. Frames of the video are localized on the map, intersections are detected, and videos are segmented. Turning views at intersections are synthesized. By connecting the video segments following the specified movement in an area, we can watch a walking view along a street. The interface allows for easy exploration of a target area. It can also show virtual billboards in the view.
Shoichiro YAMASAKI Tomoko K. MATSUSHIMA
The present paper proposes orthogonal variable spreading factor codes over finite fields for multi-rate communications. The proposed codes have layered structures that combine sequences generated by discrete Fourier transforms over finite fields, and have various code lengths. The design method for the proposed codes and examples of the codes are shown.
Shinnosuke KURATA Toshinori OTAKA Yusuke KAMEDA Takayuki HAMAMOTO
We propose a HDR (high dynamic range) reconstruction method in an image sensor with a pixel-parallel ADC (analog-to-digital converter) for non-destructively reading out the intermediate exposure image. We report the circuit design for such an image sensor and the evaluation of the basic HDR reconstruction method.
Chen LI Junjun ZHENG Hiroyuki OKAMURA Tadashi DOHI
Utilization data (a kind of incomplete data) is defined as the fraction of a fixed period in which the system is busy. In computer systems, utilization data is very common and easily observable, such as CPU utilization. Unlike inter-arrival times and waiting times, it is more significant to consider the parameter estimation of transaction-based systems with utilization data. In our previous work [7], a novel parameter estimation method using utilization data for an Mt/M/1/K queueing system was presented to estimate the parameters of a non-homogeneous Poisson process (NHPP). Since NHPP is classified as a simple counting process, it may not fit actual arrival streams very well. As a generalization of NHPP, Markovian arrival process (MAP) takes account of the dependency between consecutive arrivals and is often used to model complex, bursty, and correlated traffic streams. In this paper, we concentrate on the parameter estimation of an MAP/M/1/K queueing system using utilization data. In particular, the parameters are estimated by using maximum likelihood estimation (MLE) method. Numerical experiments on real utilization data validate the proposed approach and evaluate the effective traffic intensity of the arrival stream of MAP/M/1/K queueing system. Besides, three kinds of utilization datasets are created from a simulation to assess the effects of observed time intervals on both estimation accuracy and computational cost. The numerical results show that MAP-based approach outperforms the exiting method in terms of both the estimation accuracy and computational cost.
Kohei ITO Kensuke IIZUKA Kazuei HIRONAKA Yao HU Michihiro KOIBUCHI Hideharu AMANO
Multi-FPGA systems have gained attention because of their high performance and power efficiency. A multi-FPGA system called Flow-in-Cloud (FiC) is currently being developed as an accelerator of multi-access edge computing (MEC). FiC consists of multiple mid-range FPGAs tightly connected by high-speed serial links. Since time-critical jobs are assumed in MEC, a circuit-switched network with static time-division multiplexing (STDM) switches has been implemented on FiC. This paper investigates techniques of enhancing the interconnection performance of FiC. Unlike switching fabrics for Network on Chips or parallel machines, economical multi-FPGA systems, such as FiC, use Xilinx Aurora IP and FireFly cables with multiple lanes. We adopted the link aggregation and the slot distribution for using multiple lanes. To mitigate the bottleneck between an STDM switch and user logic, we also propose a multi-ejection STDM switch. We evaluated various combinations of our techniques by using three practical applications on an FiC prototype with 24 boards. When the number of slots is large and transferred data size is small, the slot distribution was sometimes more effective, while the link aggregation was superior for other most cases. Our multi-ejection STDM switch mitigated the bottleneck in ejection ports and successfully reduced the number of time slots. As a result, by combining the link aggregation and multi-ejection STDM switch, communication performance improved up to 7.50 times with few additional resources. Although the performance of the fast Fourier transform with the highest communication ratio could not be enhanced by using multiple boards when a lane was used, 1.99 times performance improvement was achieved by using 8 boards with four lanes and our multi-ejection switch compared with a board.
Ryutaroh MATSUMOTO Manabu HAGIWARA
This paper surveys development of quantum error correction. With the familiarity with conventional coding theory and tensor product in multi-linear algebra, this paper can be read in a self-contained manner.