检索结果-内蒙古大学图书馆

Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xiang Yang, Yimin Guo, Zhichang Zhou, Zhili Liu, Yu Pang, Qixiang Du, Shan The Dept. of Computer Science Lakehead University Thunder BayON Canada The Dept. of electrical and computer engineering Western University LondonON Canada The School of Mathematics Harbin Institute of Technology Hei Long Jiang China The School of Computer and Software Nanjing University of Information Science and Technology Jiangsu China The School of Microelectronics Tianjin University Tianjin China The Okanagan College KelownaBC Canada The Dept. of Comp. Sci. Math Physics & Statistics The University of British Columbia OkanaganBC Canada

Deep Convolutional Neural Networks (DCNNs) have exhibited impressive performance on image super-resolution tasks. However, these deep learning-based super-resolution methods perform poorly in real-world super-resolution tasks, where the paired high-resolution and low-resolution images are unavailable and the low-resolution images are degraded by complicated and unknown kernels. To break these limitations, we propose the Unsupervised Bi-directional Cycle Domain Transfer Learning-based Generative Adversarial Network (UBCDTL-GAN), which consists of an Unsupervised Bi-directional Cycle Domain Transfer Network (UBCDTN) and the Semantic Encoder guided Super Resolution Network (SESRN). First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain. Second, the SESRN has the ability to super-resolve the approximated real-like LR image to a photo-realistic HR image. Extensive experiments on unpaired real-world image benchmark datasets demonstrate that the proposed method achieves superior performance compared to state-of-the-art methods. © 2022, CC BY.

关键词： Convolutional neural networks

Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jinze Bai, Yan Lou, Yihang Linghu, Xiongkun He, Jianzhong Xu, Shaoyun Bai, Tao School of Integrated Circuits University of Chinese Academy of Sciences Beijing China School of Computer Science Peking University Beijing China Intelligent Vision Dept Huawei Technologies Beijing China Department of Electronic Engineering Tsinghua University Beijing China Institute of Microelectronics Chinese Academy of Sciences Beijing China

Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the wellknown catastrophic forgetting problem. Existing researches mainly utilize the image information, such as storing the image knowledge of previous tasks or limiting classifiers updating. However, they ignore analyzing the informative and less noisy text information of class labels. In this work, we propose leveraging the label-text information by adopting the memory prompt. The memory prompt can learn new data sequentially, and meanwhile store the previous knowledge. Furthermore, to optimize the memory prompt without undermining the stored knowledge, we propose a stimulation-based training strategy. It optimizes the memory prompt depending on the image embedding stimulation, which is the distribution of the image embedding elements. Experiments show that our proposed method outperforms all prior state-of-the-art approaches, significantly mitigating the catastrophic forgetting and overfitting problems. © 2022, CC BY.

关键词： Classification (of information)

Optical self-cooling of a membrane oscillator in a cavity optomechanical experiment at room temperature

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Vezio, P. Bonaldi, M. Borrielli, A. Marino, F. Morana, B. Sarro, P.M. Serra, E. Marin, F. I-50019 Italy Institute of Materials for Electronics and Magnetism Nanoscience-Trento-FBK Division Povo Trento38123 Italy Trento Institute for Fundamental Physics and Application Povo TrentoI-38123 Italy CNR-INO largo Enrico Fermi 6 FirenzeI-50125 Italy I-50019 Italy Dept. of Microelectronics and Computer Engineering ECTM/DIMES Delft University of Technology Feldmanweg 17 Delft2628 CT Netherlands I-50019 Italy

Thermal noise is a major obstacle to observing quantum behavior in macroscopic systems. To mitigate its effect, quantum optomechanical experiments are typically performed in a cryogenic environment. However, this condition represents a considerable complication in the transition from fundamental research to quantum technology applications. It is therefore interesting to explore the possibility of achieving the quantum regime in room temperature experiments. In this work we test the limits of sideband cooling vibration modes of a SiN membrane in a cavity optomechanical experiment. We obtain an effective temperature of a few mK, corresponding to a phononic occupation number of around 100. We show that further cooling is prevented by the excess classical noise of our laser source, and we outline the road toward the achievement of ground state cooling, Copyright © 2023, The Authors. All rights reserved.

关键词： Cooling

DOA estimation for transmit beamspace MIMO radar via tensor decomposition with Vandermonde factor matrix

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Feng Morency, Matthew W. Vorobyov, Sergiy A. School of Information and Electronics Beijing Institute of Technology Beijing100081 China Department of Signal Processing and Acoustics Aalto University Espoo02150 Finland Dept. Microelectronics School of Electrical Engineering Mathematics and Computer Science Delft University of Technology Mekelweg 4 Delft2628 CD Netherlands

We address the problem of tensor decomposition in application to direction-of-arrival (DOA) estimation for transmit beamspace (TB) multiple-input multiple-output (MIMO) radar. A general 4-order tensor model that enables computationally efficient DOA estimation is designed. Whereas other tensor decomposition-based methods treat all factor matrices as arbitrary, the essence of the proposed DOA estimation method is to fully exploit the Vandermonde structure of the factor matrices to take advantage of the shift-invariance between and within different subarrays. Specifically, the received signal of TB MIMO radar is expressed as a 4-order tensor. Depending on the target Doppler shifts, the constructed tensor is reshaped into two distinct 3-order tensors. A computationally efficient tensor decomposition method is proposed to decompose the Vandermonde factor matrices. The generators of the Vandermonde factor matrices are computed to estimate the phase rotations between subarrays, which can be utilized as a look-up table for finding target DOA. It is further shown that our proposed method can be used in a more general scenario where the subarray structures can be arbitrary but identical. The proposed DOA estimation method requires no prior information about the tensor rank and is guaranteed to achieve precise decomposition result. Simulation results illustrate the performance improvement of the proposed DOA estimation method as compared to conventional DOA estimation techniques for TB MIMO Radar. © 2021, CC0.

关键词： Tensors

Energy Adaptive Convolution Neural Network Using Dynamic Partial Reconfiguration

学校读者我要写书评

暂无评论

Energy Adaptive Convolution Neural Network Using Dynamic Par...

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Eman Youssef Hamed A. Elsemary Magdy A. El-Moursy Ahmed Khattab Hassan Mostafa Microelectronics Department Electronics Research Institute (ERI) Cairo Egypt Computer Engineering Dept Prince Sattam Bin Abdulaziz University KSA Design Creation Division Mentor Graphics Cairo Egypt Electronics and Communications Engineering Faculty of Engineering Cairo University Giza Egypt

ISBN: (数字)9781728180588

ISBN: (纸本)9781728180595

Convolutional Neural Network (CNN) is a good candidate for computer vision applications. CNN is well known for its great classification accuracy at image recognition tasks. The cost of CNN is its large power consumption as it needs a lot of multiplication and addition operations. Approximation can reduce the power consumption. CNNs can be implemented by CPUs, GPUs or FPGAs. In this paper, the proposed CNN is implemented on Xilinx XC7Z020 FPGA and is trained to recognize MNIST dataset This CNN is approximated through quantization which reduces the accuracy only by 0.53% while using 7-bits for the implementation. A reduction of 2.7X is achieved in energy consumption compared to the conventional design which uses 16-bits. Dynamic Partial Reconfiguration (DPR) reconfigures the FPGA during the run time with appropriate power consumption design if the battery level decreases. This enables recognition applications to run with low power budget but with sacrificing minor accuracy instead of termination.

关键词： Field programmable gate arrays Convolution Hardware Biological neural networks Training Image recognition Neurons

Active feedback cooling of a SiN membrane resonator by electrostatic actuation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Borrielli, Antonio Bonaldi, Michele Serra, Enrico Sarro, Pasqualina Maria Morana, Bruno Institute of Materials for Electronics and Magnetism IMEM-CNR Trento unit c/o Fondazione Bruno Kessler Via alla Cascata 56/C Povo TrentoIT-38123 Italy Dept. of Microelectronics and Computer Engineering ECTM DIMES Delft University of Technology Feldmanweg 17 Delft2628 CT Netherlands Trento Institute for Fundamental Physics and Application Povo Trento38123 Italy

Feedback-based control techniques are useful tools in precision measurements as they allow to actively shape the mechanical response of high quality factor oscillators used in force detection measurements. In this paper we implement a feedback technique on a high-stress low-loss SiN membrane resonator, exploiting the charges trapped on the dielectric membrane. A properly delayed feedback force (dissipative feedback) enables the narrowing of the thermomechanical displacement variance in a similar manner to the cooling of the normal mechanical mode down to an effective temperature Te f f. In the experiment here reported we started from room temperature and gradually increasing the feedback gain we were able to cool down the first normal mode of the resonator to a minimum temperature of about 124mK. This limit is imposed by our experimental set-up and in particular by the the injection of the read-out noise into the feedback. We discuss the implementation details and possible improvements to the technique. Copyright © 2021, The Authors. All rights reserved.

关键词： Resonators

Cost Modelling for Vectorization on ARM

学校读者我要写书评

暂无评论

Cost Modelling for Vectorization on ARM

2018 IEEE International Conference on Cluster Computing, CLUSTER 2018

作者： Pohl, Angela Cosenza, Biagio Juurlink, Ben Dept. of Computer Engineering and Microelectronics Technische Universität Berlin Germany

ISBN: (纸本)9781538683194

When applying a code transformation to optimize for performance, compilers need to assess its profitability beforehand. For this purpose, they utilize cost models, which compare the cost, an abstract measure of the code, before and after the transformation. If the cost is lower after the transformation, it will be applied. Exact cost modelling is therefore critical to avoid slowdowns or missed opportunities for speedups. In this work, we analyze the accuracy of LLVM's loop-level vectorization (LLV) cost model, and show the benefit of modelling speedup instead of instruction costs for higher vectorization rates and smaller execution times. The presented approach is portable to other compilers and hardwares as well. © 2018 IEEE.

关键词： Cosine transforms

Reduced graphene oxide tattoo as wearable proximity sensor

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kedambaimoole, Vaishakh Kumar, Neelotpala Shirhatti, Vijay Nuthalapati, Suresh Kumar, Saurabh Nayak, Mangalore Manjunatha Sen, Prosenjit Akinwande, Deji Rajanna, Konandur Dept of Instrumentation and Applied Physics Indian Institute of Science Bangalore560012 India Centre for Nano Science and Engineering Indian Institute of Science Bangalore560012 India Microelectronics Research Center Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX United States

The human body is punctuated with wide array of sensory systems that provide a high evolutionary advantage by facilitating formation of a detailed picture of the immediate surroundings. The sensors range across a wide spectrum, acquiring input from non-contact audio-visual means to contact based input via pressure and temperature. The ambit of sensing can be extended further by imparting the body with increased non-contact sensing capability through the phenomenon of electrostatics. Here we present graphene-based tattoo sensor for proximity sensing, employing the principle of electrostatic gating. The sensor shows a remarkable change in resistance upon exposure to objects surrounded with static charge on them. Compared to prior work in this field, the sensor has demonstrated the highest recorded proximity detection range of 20 cm. It is ultrathin, highly skin conformal and comes with a facile transfer process such that it can be tattooed on highly curvilinear rough substrates like the human skin, unlike other graphene-based proximity sensors reported before. Present work details the operation of wearable proximity sensor while exploring the effect of mounting body on the working mechanism. A possible role of the sensor as an alerting system against unwarranted contact with objects in public places especially during the current SARS-CoV-2 pandemic has also been explored in the form of an LED bracelet whose color is controlled by the proximity sensor attached to it. © 2020, CC BY.

关键词： Graphene

Enhanced Absorption in Amorphous Silicon Solar Cells Using Plasmonic and Photonic Crystals – Measurement and Simulation

学校读者我要写书评

暂无评论

MRS Online Proceedings Library 2019年第1期1248卷 503-509页

作者： Curtin, Benjamin Biswas, Rana Dalal, Vikram Microelectronics Research Center Dept. of Electrical and Computer Engineering Iowa State University Ames USA Dept. of Physics & Astronomy Ames Lab Iowa State University Ames USA

We develop experimentally and theoretically plasmonic and photonic crystals for enhancing thin film silicon solar cells. Thin film amorphous silicon (a-Si:H) solar cells suffer from decreased absorption of red and near-infrared photons, where the photon absorption length is large. Simulations predict maximal light absorption for a pitch of 700-800 nm for photonic crystal hole arrays in silver or ZnO/Ag back reflectors, with absorption increases of ~12%. The photonic crystal improves over the ideal randomly roughened back reflector (or the ‘4n2 limit’) at wavelengths near the band edge. We fabricated metallic photonic crystal back-reflectors using photolithography and reactive-ion etching. We conformally deposited a-Si:H solar cells on triangular lattice hole arrays of pitch 760 nm on silver back-reflectors. Electron microscopy demonstrates excellent long range periodicity and conformal a-Si:H growth. The measured quantum efficiency increases by 7-8 %, relative to a flat reflector reference device, with enhancement factors exceeding 6 at near-infrared wavelengths. The photonic crystal back reflector strongly diffracts light and increases optical path lengths of solar photons.

关键词： Si optical properties energy generation