检索结果-内蒙古大学图书馆

An Energy Efficient Carry-Free Inner Product Unit

学校读者我要写书评

暂无评论

An Energy Efficient Carry-Free Inner Product Unit

Signal, information and Data {1. (ICSIDP), IEEE International Conference on

作者： Wen Yan Miloš D. Ercegovac Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China University of California Los Angeles CA USA

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

An energy efficient truncated inner product unit is proposed in this paper. The proposed unit is pipelined and processes the m pairs of n-bit operands in serial, so that only one unit is required and it can be reused in each recurrence. Truncated inner product is produced so that no accumulation is needed for the lower part. The array reduction unit is bit-level pipelined to improve throughput and reduce the initial delay. A two-level [4:2] adder is proposed to accumulate redundant vectors with non-uniform input arrival. The proposed inner product is compared with other truncated inner product units using fully merged arithmetic, partially merged arithmetic and the counter based inner product for different precision and vector length. Our proposed inner product unit has significant reduction in area, power and energy.

关键词：

A sub-pixel level map projection conversion method for high resolution of GF3 satellite products 12

学校读者我要写书评

暂无评论

A sub-pixel level map projection conversion method for high ...

1.th European Conference on Synthetic Aperture Radar, EUSAR 201.

作者： Wang, Wentao Liu, Jiayin Huang, Lijia Key Laboratory of Technology on Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783800746361

The GF-3 satellite launched in August 201., is a C-band synthetic aperture radar(SAR) in China. With a resolution up to 1.m, GF-3 SAR imagery have made feasible the generation large-scale high resolution maps which need a high precision image registration technique. However, different remote sensing data usually have different geocoded formats. It causes misregistration when register SAR image with different projection formats. This paper discusses the method that convert the images from various projection coordinate to the unified geographic coordinate with a conversion accuracy of sub-pixel level. © VDE VERLAG GMBH • Berlin • Offenbach.

关键词： Synthetic aperture radar

Progressive unsupervised person re-identification by tracklet association with spatio-temporal regularization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xie, Qiaokang Zhou, Wengang Qi, Guo-Jun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Huawei Cloud EI Product Department Huawei Noah's Ark Laboratory

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model. To facilitate the study, we have collected a new 4K UHD video dataset named Campus-4K with full frames and full spatio-temporal {1.. Experimental results show that with the spatio-temporal constraint in the training phase, the proposed approach outperforms the state-of-the-art unsupervised methods by notable margins on DukeMTMC-reID, and achieves competitive performance to fully supervised methods on both DukeMTMC-reID and Campus-4K datasets. Copyright © 201., The Authors. All rights reserved.

关键词： Cameras

Transform-Invariant Convolutional Neural Networks for Image Classification and Search

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation & Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https: ACM ISBN 978-1.4503-21.8-9. Copyright © 201., The Authors. All rights reserved.

关键词： Image recognition

Patch reordering: A novel way to achieve rotation and translation invariance in convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shen, Xu Tian, Xinmei Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street UltimoNSW2007 Australia

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the model from the need to learn them. To enable the model to focus on learning the content of objects other than their locations, we propose to conduct patch ranking of the feature maps before feeding them into the next layer. When patch ranking is combined with convolution and pooling operations, we obtain consistent representations despite the location of meaningful objects in input. We show that the patch ranking module improves the performance of the CNN on many benchmark tasks, including MNIST digit recognition, large-scale image recognition, and image retrieval. The code is available at https://***//jasonustc/caffe-multigpu/tree/TICNN. Copyright © 201., The Authors. All rights reserved.

关键词： Convolution

Parameter prediction method of SAR target simulation based on convolutional neural networks 12

学校读者我要写书评

暂无评论

Parameter prediction method of SAR target simulation based o...

1.th European Conference on Synthetic Aperture Radar, EUSAR 201.

作者： Shengren, Niu Xiaolan, Qiu Lingxiao, Peng Bin, Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute ofElectronics Chinese Academy of Sciences University of Chinese Academy of Sciences China Suzhou Institute Institute of Electronics Chinese Academy of Sciences China

ISBN: (纸本)9783800746361

SAR image simulation plays a useful role in SAR target interpretation and recognition. The current SAR target simulation methods require high precision of models and simulation parameters, and are only forward processes which lack the feedback adjustment of real image. In this paper, a method of predicting simulation parameters from real images is proposed, which is based on convolutional neural networks(CNN). The architecture and the loss function of the CNN are modified to obtain better performance of the parameter inversion. From the simulation results, the predicted parameters improve the similarity between the simulation images and the real images. © VDE VERLAG GMBH Â Berlin Â Offenbach.

关键词： Synthetic aperture radar

Bell State Preparation Based on Switching Between Quantum system Models

学校读者我要写书评

暂无评论

Journal of systems Science & Complexity 2017年第2期30卷 347-356页

作者： ZHOU Juan KUANG Sen CONG Shuang Department of Automation University of Science and Technology of ChinaHefei 230027China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science

For the preparation of any target Bell state under continuous quantum measurement, this paper proposes a method which achieves the control objective by switching between two different models or by switching between two control channels under one model. Proper control Hamiltonians are selected for the two system models, a switching strategy between the two models is designed, and the stability of the whole switching system is proved in theory. For a given target Bell state, the effectiveness of the proposed switching control strategy between different models is illustrated through simulation experiments.

关键词： Bell state model switching quantum systems switching strategy.

Real-time correlation tracking via joint model compression and transfer

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Ning Zhou, Wengang Song, Yibing Ma, Chao Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei China Tencent AI Lab Shenzhen China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Correlation filters (CF) have received considerable attention in visual tracking because of their computational efficiency. Leveraging deep features via off-the-shelf CNN models (e.g., VGG), CF trackers achieve state-of-the-art performance while consuming a large number of computing resources. This limits deep CF trackers to be deployed to many mobile platforms on which only a single-core CPU is available. In this paper, we propose to jointly compress and transfer off-the-shelf CNN models within a knowledge distillation framework. We formulate a CNN model pretrained from the image classification task as a teacher network, and distill this teacher network into a lightweight student network as the feature extractor to speed up CF trackers. In the distillation process, we propose a fidelity loss to enable the student network to maintain the representation capability of the teacher network. Meanwhile, we design a tracking loss to adapt the objective of the student network from object recognition to visual tracking. The distillation process is performed offline on multiple layers and adaptively updates the student network using a background-aware online learning scheme. Extensive experiments on five challenging datasets demonstrate that the lightweight student network accelerates the speed of state-of-the-art deep CF trackers to real-time on a single-core CPU while maintaining almost the same tracking accuracy. Copyright © 201., The Authors. All rights reserved.

关键词： Object recognition

Predictive auto-encoding network for blind stereoscopic image quality assessment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Jiahua Zhou, Wei Chen, Zhibo Ling, Suiyi Le Callet, Patrick CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China quipe Image Perception et Interaction Laboratoire des Sciences du Numrique de Nantes Universit de Nantes Nantes44300 France

Stereoscopic image quality assessment (SIQA) has encountered non-trivial challenges due to the fast proliferation of 3D contents. In the past years, deep learning oriented SIQA methods have emerged and achieved spectacular performance compared to conventional algorithms which are only relied on extracting hand-crafted features. However, most existing deep SIQA evaluators are not specifically built for stereoscopic content and consider little prior domain knowledge of the 3D human visual system (HVS) in network design. In this paper, to better simulate the binocular rivalry phenomenon, we propose a Predictive Auto-encoDing Network (PAD-Net) for blind/No-Reference stereoscopic image quality assessment (NR-SIQA). The proposed encoder-decoder architecture is inspired by the predictive coding theory that the cognition system tries to match bottom-up visual signal with top-down predictions. Besides, we design the Siamese framework to mimic the binocular rivalry in the 3D HVS based on the likelihood and prior maps generated from the predictive coding process. Extensive experimental results on three publicly available stereoscopic image quality databases demonstrate that the devised approach outperforms state-of-the-art algorithms for predicting the perceptual quality of both symmetrically and asymmetrically distorted stereoscopic images with various distortion types. Copyright © 201., The Authors. All rights reserved.

关键词： Network coding