“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Acknowledgements: We would like to thank the following for contributions and suggestions: Bill Baxter, Brian Templeton, Christian Rishoj, Christian Schroppel Douglas L. Theobald, Esben Hoegh-Rasmussen, Glynne Casteel, Jan Larsen, Jun Bin Gao, Jurgen Struckmeier, Kamil Dedecius, Korbinian Strimmer, Lars Christiansen, Lars Kai Hansen, Leland Wilkinson, Liguo He, Loic Thibaut, Miguel Barao, Ole Winther, Pavel Sakov, Stephan Hattinger, Vasile Sima, Vincent Rabaud, Zhaoshui He. We would also like thank The Oticon Foundation for funding our PhD studies.

The Matrix Cookbook

The vision of next generation 5G wireless communications lies in providing very high data rates (typically of Gbps order), extremely low latency, manifold increase in base station capacity, and significant improvement in users’ perceived quality of service (QoS), compared to current 4G LTE networks. Ever increasing proliferation of smart devices, introduction of new emerging multimedia applications, together with an exponential rise in wireless data (multimedia) demand and usage is already creating a significant burden on existing cellular networks. 5G wireless systems, with improved data rates, capacity, latency, and QoS are expected to be the panacea of most of the current cellular networks’ problems. In this survey, we make an exhaustive review of wireless evolution toward 5G networks. We first discuss the new architectural changes associated with the radio access network (RAN) design, including air interfaces, smart antennas, cloud and heterogeneous RAN. Subsequently, we make an in-depth survey of underlying novel mm-wave physical layer technologies, encompassing new channel model estimation, directional antenna design, beamforming algorithms, and massive MIMO technologies. Next, the details of MAC layer protocols and multiplexing schemes needed to efficiently support this new physical layer are discussed. We also look into the killer applications, considered as the major driving force behind 5G. In order to understand the improved user experience, we provide highlights of new QoS, QoE, and SON features associated with the 5G evolution. For alleviating the increased network energy consumption and operating expenditure, we make a detail review on energy awareness and cost efficiency. As understanding the current status of 5G implementation is important for its eventual commercialization, we also discuss relevant field trials, drive tests, and simulation experiments. Finally, we point out major existing research issues and identify possible future research directions.

Next Generation 5G Wireless Networks: A Comprehensive Survey

This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Coverage control for mobile sensing networks

This book provides a broad survey of models and efficient algorithms for Nonnegative Matrix Factorization (NMF) This includes NMFs various extensions and modifications, especially Nonnegative Tensor Factorizations (NTF) and Nonnegative Tucker Decompositions (NTD) NMF/NTF and their extensions are increasingly used as tools in signal and image processing, and data analysis, having garnered interest due to their capability to provide new insights and relevant information about the complex latent relationships in experimental data sets It is suggested that NMF can provide meaningful components with physical interpretations; for example, in bioinformatics, NMF and its extensions have been successfully applied to gene expression, sequence analysis, the functional characterization of genes, clustering and text mining As such, the authors focus on the algorithms that are most useful in practice, looking at the fastest, most robust, and suitable for large-scale models Key features: Acts as a single source reference guide to NMF, collating information that is widely dispersed in current literature, including the authors own recently developed techniques in the subject area Uses generalized cost functions such as Bregman, Alpha and Beta divergences, to present practical implementations of several types of robust algorithms, in particular Multiplicative, Alternating Least Squares, Projected Gradient and Quasi Newton algorithms Provides a comparative analysis of the different methods in order to identify approximation error and complexity Includes pseudo codes and optimized MATLAB source codes for almost all algorithms presented in the book The increasing interest in nonnegative matrix and tensor factorizations, as well as decompositions and sparse representation of data, will ensure that this book is essential reading for engineers, scientists, researchers, industry practitioners and graduate students across signal and image processing; neuroscience; data mining and data analysis; computer science; bioinformatics; speech processing; biomedical engineering; and multimedia

Nonnegative Matrix and Tensor Factorizations: Applications to Exploratory Multi-way Data Analysis and Blind Source Separation

For improving coding efficiency, a new predictive vector quantization (VQ) method was proposed in this paper Two codebooks with different dimensionalities and different size were employed in our algorithm The defined blocks are first classified based on variance For smooth areas, the current processing vectors are sampled into even column vectors and odd column vectors The even column vectors are encoded with the lower-dimensional and smaller size codebook The odd ones are predicted using the decoded pixels from intra-blocks and inter-blocks at the decoder For edge areas, the current processing vectors are encoded with traditional codebook to maintain the image quality An efficient method for codebook design was also presented to improve the quality of the resulted codebook The experimental comparisons with the other methods show good performance of our algorithm

A new predictive vector quantization method using a smaller codebook

FOCal Underdetermined System Solver (FOCUSS) is a powerful tool for sparse representation and underdetermined inverse problems, which is extremely easy to implement. In this paper, we give a comprehensive convergence analysis on the FOCUSS algorithm towards establishing a systematic convergence theory by providing three primary contributions as follows. First, we give a rigorous derivation for this algorithm exploiting the auxiliary function. Then, we prove its convergence. Third, we systematically study its convergence rate with respect to the sparsity parameter p and demonstrate its convergence rate by numerical experiments.

Convergence analysis of the FOCUSS algorithm

In this paper, a spatial co-occurrence matrix (SCM) is proposed for representing the spatial relationship of semantic objects in images. The proposed SCM is established on both vertical and horizontal directions of interesting objects from the prototype spatial arrangement in images. The spatial relationships among objects can be retained directly in the prototype spatial arrangements, and then implicitly embedded in the proposed SCM. Furthermore, the calculation of spatial similarity among images can be implemented by calculating the distance between the SCMs.

Spatial relationship of image semantics objects

In this paper, an efficient adaptive de-blocking algorithm is proposed to reduce blocking artifacts. Blocking artifacts are modeled as step functions and then the image blocks are divided into three categories: smooth blocks, texture blocks and edge blocks. For smooth blocks, the expression of amplitude of blocking artifacts is educed firstly in our algorithm, and then the adaptive smooth filter according to the amplitude of blocking artifacts and the smooth degree function is proposed to reduce blocking artifacts. For the texture blocks and edge blocks, the Sigma filter is used to smooth the block boundaries. The experiment results show that the proposed algorithm reduces the blocking artifacts effectively and preserves the original edges faithfully.

An efficient adaptive de-blocking algorithm

For complexity in the process of vector quantization image encoding, a new fast codebook search algorithm based on wavelet transform is presented in this paper. Squared Euclidean distance is used as distortion measurement. In the algorithm, a reasonable initial codeword is chosen for the input vector firstly. The relationship between the input vector and codeword, as well as relationship among codewords and characteristics of vectors in wavelet domain, are then utilized to reject impossible matched codewords. The best-matched codeword for the input vector is finally obtained by reducing the search space gradually. The experimental results show the proposed algorithm significantly reduces the complexity of VQ encoding without compromising the encoded image quality with little preprocessing and memory cost.

Shengli Xie

Papers

A new predictive vector quantization method using a smaller codebook

Convergence analysis of the FOCUSS algorithm

Spatial relationship of image semantics objects

An efficient adaptive de-blocking algorithm

A wavelet-based fast search algorithm for vector quantization