scholarly journals Dynamic Instance Normalization for Arbitrary Style Transfer

2020 ◽  
Vol 34 (04) ◽  
pp. 4369-4376 ◽  
Author(s):  
Yongcheng Jing ◽  
Xiao Liu ◽  
Yukang Ding ◽  
Xinchao Wang ◽  
Errui Ding ◽  
...  
Keyword(s):  
State Of The Art ◽  
Computational Cost ◽  
Mobile Terminal ◽  
Reduction Factor ◽  
Affine Transformations ◽  
Style Transfer ◽  
Flexible Support ◽  
Normalization Methods ◽  
Constrained Environments ◽  
First Time

Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way. Such manually-defined nature eventually results in the high-cost and shared encoders for both style and content encoding, making style transfer systems cumbersome to be deployed in resource-constrained environments like on the mobile-terminal side. In this paper, we propose a new and generalized normalization module, termed as Dynamic Instance Normalization (DIN), that allows for flexible and more efficient arbitrary style transfers. Comprising an instance normalization and a dynamic convolution, DIN encodes a style image into learnable convolution parameters, upon which the content image is stylized. Unlike conventional methods that use shared complex encoders to encode content and style, the proposed DIN introduces a sophisticated style encoder, yet comes with a compact and lightweight content encoder for fast inference. Experimental results demonstrate that the proposed approach yields very encouraging results on challenging style patterns and, to our best knowledge, for the first time enables an arbitrary style transfer using MobileNet-based lightweight architecture, leading to a reduction factor of more than twenty in computational cost as compared to existing approaches. Furthermore, the proposed DIN provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.

scholarly journals IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5541 ◽  
Author(s):  
Tom Lawrence ◽  
Li Zhang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Computational Cost ◽  
Resource Constrained ◽  
Traffic Sign ◽  
Constrained Environments ◽  
Scale Down ◽  
Art Performance ◽  
Iot Devices

Two main approaches exist when deploying a Convolutional Neural Network (CNN) on resource-constrained IoT devices: either scale a large model down or use a small model designed specifically for resource-constrained environments. Small architectures typically trade accuracy for computational cost by performing convolutions as depth-wise convolutions rather than standard convolutions like in large networks. Large models focus primarily on state-of-the-art performance and often struggle to scale down sufficiently. We propose a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models. IoTNet trades accuracy with computational cost differently from existing methods by factorizing standard 3 × 3 convolutions into pairs of 1 × 3 and 3 × 1 standard convolutions, rather than performing depth-wise convolutions. We benchmark IoTNet against state-of-the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource-constrained environments. We compare model accuracy and the number of floating-point operations (FLOPs) performed as a measure of efficiency. We report state-of-the-art accuracy improvement over MobileNetV2 on CIFAR-10 of 13.43% with 39% fewer FLOPs, over ShuffleNet on Street View House Numbers (SVHN) of 6.49% with 31.8% fewer FLOPs and over MobileNet on German Traffic Sign Recognition Benchmark (GTSRB) of 5% with 0.38% fewer FLOPs.

scholarly journals State-of-the-Art Char Production with a Focus on Bark Feedstocks: Processes, Design, and Applications

Processes ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 87
Author(s):  
Ali Umut Şen ◽  
Helena Pereira
Keyword(s):  
State Of The Art ◽  
Lignocellulosic Materials ◽  
Heating Rates ◽  
Production Methods ◽  
Slow Pyrolysis ◽  
Production Studies ◽  
Lignocellulosic Feedstocks ◽  
Thermochemical Method ◽  
Superior Surface ◽  
First Time

In recent years, there has been a surge of interest in char production from lignocellulosic biomass due to the fact of char’s interesting technological properties. Global char production in 2019 reached 53.6 million tons. Barks are among the most important and understudied lignocellulosic feedstocks that have a large potential for exploitation, given bark global production which is estimated to be as high as 400 million cubic meters per year. Chars can be produced from barks; however, in order to obtain the desired char yields and for simulation of the pyrolysis process, it is important to understand the differences between barks and woods and other lignocellulosic materials in addition to selecting a proper thermochemical method for bark-based char production. In this state-of-the-art review, after analyzing the main char production methods, barks were characterized for their chemical composition and compared with other important lignocellulosic materials. Following these steps, previous bark-based char production studies were analyzed, and different barks and process types were evaluated for the first time to guide future char production process designs based on bark feedstock. The dry and wet pyrolysis and gasification results of barks revealed that application of different particle sizes, heating rates, and solid residence times resulted in highly variable char yields between the temperature range of 220 °C and 600 °C. Bark-based char production should be primarily performed via a slow pyrolysis route, considering the superior surface properties of slow pyrolysis chars.

scholarly journals UV Inscription and Pressure Induced Long-Period Gratings through 3D Printed Amplitude Masks

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1977
Author(s):  
Ricardo Oliveira ◽  
Liliana M. Sousa ◽  
Ana M. Rocha ◽  
Rogério Nogueira ◽  
Lúcia Bilro
Keyword(s):  
State Of The Art ◽  
Low Cost ◽  
Resonance Wavelength ◽  
Complex Structures ◽  
Pressing Method ◽  
Long Period ◽  
Long Period Gratings ◽  
3D Printed ◽  
Mechanical Pressing ◽  
First Time

In this work, we demonstrate for the first time the capability to inscribe long-period gratings (LPGs) with UV radiation using simple and low cost amplitude masks fabricated with a consumer grade 3D printer. The spectrum obtained for a grating with 690 µm period and 38 mm length presented good quality, showing sharp resonances (i.e., 3 dB bandwidth < 3 nm), low out-of-band loss (~0.2 dB), and dip losses up to 18 dB. Furthermore, the capability to select the resonance wavelength has been demonstrated using different amplitude mask periods. The customization of the masks makes it possible to fabricate gratings with complex structures. Additionally, the simplicity in 3D printing an amplitude mask solves the problem of the lack of amplitude masks on the market and avoids the use of high resolution motorized stages, as is the case of the point-by-point technique. Finally, the 3D printed masks were also used to induce LPGs using the mechanical pressing method. Due to the better resolution of these masks compared to ones described on the state of the art, we were able to induce gratings with higher quality, such as low out-of-band loss (0.6 dB), reduced spectral ripples, and narrow bandwidths (~3 nm).

scholarly journals Electro-Quasistatic Animal Body Communication for Untethered Rodent Biopotential Recording

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shreeya Sriram ◽  
Shitij Avlani ◽  
Matthew P. Ward ◽  
Shreyas Sen
Keyword(s):  
Lower Energy ◽  
Sensor Node ◽  
State Of The Art ◽  
The Body ◽  
Animal Body ◽  
Current State ◽  
Communication Modalities ◽  
First Time ◽  
Biopotential Recording

AbstractContinuous multi-channel monitoring of biopotential signals is vital in understanding the body as a whole, facilitating accurate models and predictions in neural research. The current state of the art in wireless technologies for untethered biopotential recordings rely on radiative electromagnetic (EM) fields. In such transmissions, only a small fraction of this energy is received since the EM fields are widely radiated resulting in lossy inefficient systems. Using the body as a communication medium (similar to a ’wire’) allows for the containment of the energy within the body, yielding order(s) of magnitude lower energy than radiative EM communication. In this work, we introduce Animal Body Communication (ABC), which utilizes the concept of using the body as a medium into the domain of untethered animal biopotential recording. This work, for the first time, develops the theory and models for animal body communication circuitry and channel loss. Using this theoretical model, a sub-inch$$^3$$ 3 [1″ × 1″ × 0.4″], custom-designed sensor node is built using off the shelf components which is capable of sensing and transmitting biopotential signals, through the body of the rat at significantly lower powers compared to traditional wireless transmissions. In-vivo experimental analysis proves that ABC successfully transmits acquired electrocardiogram (EKG) signals through the body with correlation $$>99\%$$ > 99 % when compared to traditional wireless communication modalities, with a 50$$\times$$ × reduction in power consumption.

scholarly journals Thermoelectric Sensor Coupled Yagi–Uda Nanoantenna for Infrared Detection

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 527
Author(s):  
Waleed Tariq Sethi ◽  
Olivier De Sagazan ◽  
Mohamed Himdi ◽  
Hamsakutty Vettikalladi ◽  
Saleh A. Alshebeili
Keyword(s):  
State Of The Art ◽  
Infrared Detection ◽  
Single Element ◽  
Center Wavelength ◽  
Resonance Response ◽  
Thermal Measurements ◽  
Radiation Induced ◽  
Thermoelectric Sensor ◽  
Junction Array ◽  
First Time

We present an experimental demonstration of a thermoelectric sensor coupled with a nanoantenna as an alternative option for detecting infrared energy. Two nanoantenna design (single element and an array) variations based on Yagi-Uda technology and one separate nano-thermoelectric junction array were fabricated and tested. The nanoantennas were tuned to operate and respond at a center wavelength of 1550 nm (193.5 THz) optical C-band window, but they also exhibited a resonance response when excited by lasers of various wavelengths (650 nm and 940 nm). The radiation-induced electric currents in the nanoantennas, coupled with a nano-thermoelectric sensor, produced a potential difference as per the Seebeck effect. With respect to the uniform thermal measurements of the reference nanoantenna, the experiments confirmed the detection properties of the proposed nanoantennas; the single element detected a peak percentage voltage hike of 28%, whereas the array detected a peak percentage voltage hike of 80% at the center wavelength. Compared to state-of-the-art thermoelectric designs, this was the first time that such peak percentage voltages were experimentally reported following a planar design based on the Seebeck principle.

scholarly journals Concurrent material and structure optimization of multiphase hierarchical systems within a continuum micromechanics framework

2021 ◽  
Author(s):  
Tarun Gangwar ◽  
Dominik Schillinger
Keyword(s):  
Optimization Problems ◽  
Computational Cost ◽  
Structure Optimization ◽  
Material Behavior ◽  
Hierarchical Systems ◽  
Material Optimization ◽  
Continuum Micromechanics ◽  
Benchmark Tests ◽  
Constraint Optimization Problems ◽  
First Time

AbstractWe present a concurrent material and structure optimization framework for multiphase hierarchical systems that relies on homogenization estimates based on continuum micromechanics to account for material behavior across many different length scales. We show that the analytical nature of these estimates enables material optimization via a series of inexpensive “discretization-free” constraint optimization problems whose computational cost is independent of the number of hierarchical scales involved. To illustrate the strength of this unique property, we define new benchmark tests with several material scales that for the first time become computationally feasible via our framework. We also outline its potential in engineering applications by reproducing self-optimizing mechanisms in the natural hierarchical system of bamboo culm tissue.

scholarly journals Domain Adaptation Using a Three-Way Decision Improves the Identification of Autism Patients from Multisite fMRI Data

2021 ◽  
Vol 11 (5) ◽  
pp. 603
Author(s):  
Chunlei Shi ◽  
Xianwei Xin ◽  
Jiacai Zhang
Keyword(s):  
Machine Learning ◽  
Domain Adaptation ◽  
Recognition Accuracy ◽  
State Of The Art ◽  
Autism Spectrum ◽  
Fmri Data ◽  
Target Domain ◽  
Sample Distribution ◽  
Machine Learning Methods ◽  
First Time

Machine learning methods are widely used in autism spectrum disorder (ASD) diagnosis. Due to the lack of labelled ASD data, multisite data are often pooled together to expand the sample size. However, the heterogeneity that exists among different sites leads to the degeneration of machine learning models. Herein, the three-way decision theory was introduced into unsupervised domain adaptation in the first time, and applied to optimize the pseudolabel of the target domain/site from functional magnetic resonance imaging (fMRI) features related to ASD patients. The experimental results using multisite fMRI data show that our method not only narrows the gap of the sample distribution among domains but is also superior to the state-of-the-art domain adaptation methods in ASD recognition. Specifically, the ASD recognition accuracy of the proposed method is improved on all the six tasks, by 70.80%, 75.41%, 69.91%, 72.13%, 71.01% and 68.85%, respectively, compared with the existing methods.

A hierarchical oxygen vacancy-rich WO3 with “nanowire-array-on-nanosheet-array” structure for highly efficient oxygen evolution reaction

2019 ◽  
Vol 7 (12) ◽  
pp. 6730-6739 ◽  
Author(s):  
Jinxiang Diao ◽  
Wenyu Yuan ◽  
Yu Qiu ◽  
Laifei Cheng ◽  
Xiaohui Guo
Keyword(s):  
Oxygen Vacancy ◽  
Oxygen Evolution Reaction ◽  
Oxygen Vacancies ◽  
State Of The Art ◽  
Nanowire Array ◽  
Nanowire Arrays ◽  
Nanosheet Array ◽  
Nanosheet Arrays ◽  
Array Structure ◽  
First Time

Hierarchical vertical WO3 nanowire arrays on vertical WO3 nanosheet arrays with rich oxygen vacancies were synthesized via a simple and facile method, and the outstanding OER performance which is superior to that of most reported state-of-the-art catalysts was reported for the first time.

scholarly journals Resolved Stellar Populations of the interacting galaxies of the M81 group

2016 ◽  
Vol 11 (S321) ◽  
pp. 22-24
Author(s):  
Sakurako Okamoto ◽  
Nobuo Arimoto ◽  
Annette M.N. Ferguson ◽  
Edouard J. Bernard ◽  
Mike J. Irwin ◽  
...  
Keyword(s):  
Main Sequence ◽  
Field Survey ◽  
State Of The Art ◽  
Young Stars ◽  
Interacting Galaxies ◽  
Wide Field ◽  
Red Giant ◽  
Tidal Streams ◽  
Stellar Associations ◽  
First Time

AbstractWe present the results from the state-of-the-art wide-field survey of the M81 galaxy group that we are conducting with Hyper Suprime-Cam on Subaru Telescope. Our photometry reaches about 2 mag below the tip of the red giant branch (RGB) and reveals the spatial distribution of both old and young stars over an area of 5°2around the M81. The young main-sequence (MS) stars closely follow the HI distribution and can be found in a stellar stream between M81 and NGC 3077 and in numerous outlying stellar associations. Our survey also reveals for the first time the very extended (>2 × R25) halos of RGB stars around M81, M82, and NGC 3077, as well as faint tidal streams that link these systems. The gravitational interactions between M81, M82 and NGC 3077 galaxies induced star formation in tidally stripped gas, and also significantly perturbed the older stellar components leading to disturbed halo morphologies.

A NEW LAYOUT DESIGN SYSTEM FOR MULTICHIP MODULES

1995 ◽  
Vol 06 (03) ◽  
pp. 509-538 ◽  
Author(s):  
BERNHARD M. RIESS ◽  
ANDREAS A. SCHOENE
Keyword(s):  
Efficient Algorithm ◽  
State Of The Art ◽  
Layout Design ◽  
The State ◽  
Design System ◽  
Multichip Modules ◽  
Analytical Technique ◽  
Cut Method ◽  
First Time ◽  
Three Components

A new layout design system for multichip modules (MCMs) consisting of three components is described. It includes a k-way partitioning approach, an algorithm for pin assignment, and a placement package. For partitioning, we propose an analytical technique combined with a problem-specific multi-way ratio cut method. This method considers fixed module-level pad positions and assigns the cells to regularly arranged chips on the MCM substrate. In the subsequent pin assignment step the chip-level pads resulting from cut nets are positioned on the chip borders. Pin assignment is performed by an efficient algorithm, which profits from the cell coordinates generated by the analytical technique. Global and final placement for each chip is computed by the state-of-the-art placement tools GORDIANL and DOMINO. For the first time, results for MCM layout designs of benchmark circuits with up to 100,000 cells are presented. They show a small number of required chip-level pads, which is the most restricted resource in MCM design, and short total wire lengths.

Sign in / Sign up

Export Citation Format

Share Document