检索结果-内蒙古大学图书馆

Direction-aware spatial context features for shadow detection and removal

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Hu, Xiaowei Fu, Chi-Wing Zhu, Lei Qin, Jing Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Centre for Smart Health School of Nursing Hong Kong Polytechnic University Department of Computer Science and Engineering Chinese University of Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Shadow detection and shadow removal are fundamental and challenging tasks, requiring an understanding of the global image semantics. This paper presents a novel deep neural network design for shadow detection and removal by analyzing the image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting and removing shadows. This design is developed into the DSC module and embedded in a convolutional neural network (CNN) to learn the DSC features in different levels. Moreover, we design a weighted cross entropy loss to make effective the training for shadow detection and further adopt the network for shadow removal by using a Euclidean loss function and formulating a color transfer function to address the color and luminosity inconsistency in the training pairs. We employ two shadow detection benchmark datasets and two shadow removal benchmark datasets, and perform various experiments to evaluate our method. Experimental results show that our method clearly outperforms state-of-the-art methods for both shadow detection and shadow removal. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

Image co-segmentation via multi-scale local shape transfer

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Teng, Wei Zhang, Yu Chen, Xiaowu Li, Jia He, Zhiqiang State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China International Research Institute for Multidisciplinary Science Beihang University Beijing100191 China Lenovo Research China

Image co-segmentation is a challenging task in computer vision that aims to segment all pixels of the objects from a predefined semantic category. In real-world cases, however, common foreground objects often vary greatly in appearance, making their global shapes highly inconsistent across images and difficult to be segmented. To address this problem, this paper proposes a novel co-segmentation approach that transfers patch-level local object shapes which appear more consistent across different images. In our framework, a multi-scale patch neighbourhood system is first generated using proposal flow on arbitrary image-pair, which is further refined by Locally Linear Embedding. Based on the patch relationships, we propose an efficient algorithm to jointly segment the objects in each image while transferring their local shapes across different images. Extensive experiments demonstrate that the proposed method can robustly and effectively segment common objects from an image set. On iCoseg, MSRC and Coseg-Rep dataset, the proposed approach performs comparable or better than the state-of-the-arts, while on a more challenging benchmark Fashionista dataset, our method achieves significant improvements. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

Masked Image Training for Generalizable Deep Image Denoising

学校读者我要写书评

暂无评论

Masked Image Training for Generalizable Deep Image Denoising

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Haoyu Chen Jinjin Gu Yihao Liu Salma Abdel Magid Chao Dong Qiong Wang Hanspeter Pfister Lei Zhu The Hong Kong University of Science and Technology (Guangzhou) Shanghai AI Lab The University of Sydney ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Harvard University Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The Hong Kong University of Science and Technology

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of Transformer-based models that have achieved notable state-of-the-art results on various image tasks. However, deep learning-based methods often suffer from a lack of generalization ability. For example, deep models trained on Gaussian noise may perform poorly when tested on other noise distributions. To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training. Our method involves masking random pixels of the input image and reconstructing the missing information during training. We also mask out the features in the self-attention layers to avoid the impact of training-testing inconsistency. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios. Additionally, our interpretability analysis demonstrates the superiority of our method.

关键词：

CodeRepair: PHY-layer partial packet recovery without the pain

学校读者我要写书评

暂无评论

CodeRepair: PHY-layer partial packet recovery without the pa...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Jun Huang Guoliang Xing Jianwei Niu Shan Lin Department of Comptuer Science and Engineering Michigan State University MI USA State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Electrical and Computer Engineering Stony Brook University NY USA

Prior studies show that repairing partially corrupted packets, instead of retransmitting them in their entirety, holds potential in improving the performance of 802.11 networks. However, the efficiency of existing packet recovery approaches is severely limited by various overhead associated to redundant transmission and repeated channel contention. In this paper, we propose CodeRepair, a practical coding-based protocol that recovers partially corrupted 802.11 packets without these pains. The design of CodeRepair is based on two novel ideas. First, CodeRepair pushes the limit of 802.11 PHY to piggyback parities in the padded bits of OFDM, obviating the need of transmitting extra information for error correction. Second, CodeRepair corrects errors at the PHY layer, which is significantly more efficient than traditional link-layer approaches. This is due to the fact that a single coded bit usually affects the decoding of a group of data bits in 802.11 convolutional code. As a result, CodeRepair can salvage a partially corrupted packet by correcting a small number of erroneous coded bits using the padded parities. To reduce computational cost of error recovery, CodeRepair employs single parity code for correcting coded bit errors. We propose several techniques to augment the error correcting capability of single parity code without compromising its computation efficiency. Our evaluation shows that CodeRepair recovers an average of 34% partially corrupted packets, and improves the end-to-end link goodput by 59% on lossy 802.11 links.

关键词： IEEE 802.11 Standard Decoding Receivers Reflective binary codes Convolutional codes Forward error correction OFDM

The analysis to gamma oscillations induced in high dose DHPG and spike-gamma oscillation relationship

学校读者我要写书评

暂无评论

International Journal of Advancements in Computing technology 2012年第20期4卷 553-560页

作者： Wen, Dong Lu, Chengbiao Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province Yanshan University QinhuangdaoHebei 066004 China School of Information Science and Engineering Yanshan University QinhuangdaoHebei 066004 China Institue of Electrical Engineering Yanshan University Qinhuangdao Hebei 066004 China

Neuronal oscillations in the gamma frequency range and spikes have been reported in many cortical areas in the information processing, but the role of spikes play in cortical processing remains unclear. The aim of this study was to examine the role of high dose DHPG in the generation of oscillatory field activity at gamma frequency in the medical septal diagonal band of Broca (MSDB) slice prepared from rat brain, and to determine the phase relationship between spikes and gamma oscillations. The high dose DHPG induced large amplitude field population spiking activity, which is correlated linearly with the field gamma oscillations. The relationship between timing of spikes and the phase of gamma oscillation was determined by an analysis of circular statistics. Further analysis with Rayleigh test revealed that the relationship of phase-locking between spikes and gamma rhythm is of statistical significance. These data demonstrate that DHPG-sensitive neuronal networks within medial septum are able to generate gamma oscillations which are modulated by large amplitude population spikes and phase-locking of spikes to the gamma rhythm suggest the role of memory enhancement in the presence of mGluR1 activation.

关键词： Locks (fasteners)

Learning a saliency evaluation metric using crowdsourced perceptual judgments

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xia, Changqun Li, Jia Su, Jinming Borji, Ali State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China International Research Institute for Multidisciplinary Science Beihang University Beijing China Center for Research in Computer Vision Computer Science Department University of Central Florida OrlandoFL United States

In the area of human fixation prediction, dozens of computational saliency models are proposed to reveal certain saliency characteristics under different assumptions and definitions. As a result, saliency model benchmarking often requires several evaluation metrics to simultaneously assess saliency models from multiple perspectives. However, most computational metrics are not designed to directly measure the perceptual similarity of saliency maps so that the evaluation results may be sometimes inconsistent with the subjective impression. To address this problem, this paper first conducts extensive subjective tests to find out how the visual similarities between saliency maps are perceived by humans. Based on the crowdsourced data collected in these tests, we conclude several key factors in assessing saliency maps and quantize the performance of existing metrics. Inspired by these factors, we propose to learn a saliency evaluation metric based on a two-stream convolutional neural network using crowdsourced perceptual judgements. Specifically, the relative saliency score of each pair from the crowdsourced data is utilized to regularize the network during the training process. By capturing the key factors shared by various subjects in comparing saliency maps, the learned metric better aligns with human perception of saliency maps, making it a good complement to the existing metrics. Experimental results validate that the learned metric can be generalized to the comparisons of saliency maps from new images, new datasets, new models and synthetic data. Due to the effectiveness of the learned metric, it also can be used to facilitate the development of new models for fixation prediction. Copyright © 2018, The Authors. All rights reserved.

关键词： Crowdsourcing

Enabling Communication-Efficient Federated Learning via Distributed Compressed Sensing

学校读者我要写书评

暂无评论

Enabling Communication-Efficient Federated Learning via Dist...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yixuan Guan Xuefeng Liu Tao Ren Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Laboratory for Internet Software Technologies Institute of Software Chinese Academy of Sciences Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

Federated learning (FL) trains a shared global model by periodically aggregating gradients from local devices. Communication overhead becomes a principal bottleneck in FL since participating devices usually suffer from limited bandwidth and unreliable connections in uplink transmission. To address this problem, the gradient compression methods based on compressed sensing (CS) theory have been put forward recently. However, most existing CS-based works compress gradients independently, ignoring the gradient correlations between participants or adjacent communication rounds, which constrains the achievement of higher compression rates. In view of the above observation, we propose a novel gradient compression scheme named FedDCS, guided by distributed compressed sensing (DCS) theory. Following the design philosophy of separate encoding and joint decoding in DCS, FedDCS compresses gradients for participants in each round separately while reconstructing them at the central server jointly via fully exploiting correlated gradients from the previous round, which are known as side information (SI). Benefiting from this design, reconstruction performance is significantly improved with fewer decoding errors also iterations under the identical compression rate, and the total uploading bits to achieve model convergence are considerably reduced. Theoretical analysis and extensive experiments conducted on MNIST and Fashion-MNIST both verify the effectiveness of our approach.

关键词：

Gossip-Based Indexing Ring Topology for 2-Dimension Spatial Data in Overlay Networks

学校读者我要写书评

暂无评论

Procedia Engineering 2012年 29卷 3727-3731页

作者： Z.Q. Zou Y. Wang B. Hu R.C. Wang College of Computer Nanjing University of Posts and TelecommunicationsNanjing Jiangsu 210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing Jiangsu 210003 China Key Lab of Broadband Wireless Communication and Sensor Network Technology (Nanjing University of Posts and Telecommunications) Ministry of Education Jiangsu Province Nanjing Jiangsu 210003 China Key Laboratory of Virtual Geographic Environment Ministry of Education Nanjing Normal University Nanjing 210046 China

Overlay networks are used widely in the Internet, such as retrieval and share of files, multimedia games and so on. However, in distributed system, the retrieval and share of 2-dimension spatial data still have some difficult problems and can not solve the complex retrieval of 2-dimension spatial data efficiently. This article presents a new indexing overlay networks, named 2D-Ring, which is the ring topology based on gossip for 2-dimension spatial data. The peers in our overlay networks exchange the information periodically and update each local view by constructing algorithm. 2-dimension spatial data is divided by quad-tree and mapped into control points, which are hashed into 2D-Ring by SHA-1 hash function. In such way, the problem of 2-dimension spatial data indexing is converted to the problem of searching peers in the 2D-Ring. A large of extensive experiments show that the time complexity of constructing algorithm of 2D-Ring can reach convergence logarithmically as a function of the network size and hold higher hit rate and lower query delay.

关键词： Overlay networks 2-Dimension Spatial Data Indexing Gossip

IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Jiancheng Zhou, Donghao Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Chinese University of Hong Kong Hong Kong

Single-shot face anti-spoofing (FAS) is a key technique for securing face recognition systems, and it requires only static images as input. However, single-shot FAS remains a challenging and under-explored problem due to two main reasons: 1) on the data side, learning FAS from RGB images is largely context-dependent, and single-shot images without additional annotations contain limited semantic information. 2) on the model side, existing single-shot FAS models are infeasible to provide proper evidence for their decisions, and FAS methods based on depth estimation require expensive per-pixel annotations. To address these issues, a large binocular NIR image dataset (BNI-FAS) is constructed and published, which contains more than 300,000 real face and plane attack images, and an Interpretable FAS Transformer (IFAST) is proposed that requires only weak supervision to produce interpretable predictions. Our IFAST can produce pixel-wise disparity maps by the proposed disparity estimation Transformer with Dynamic Matching Attention (DMA) block. Besides, a well-designed confidence map generator is adopted to cooperate with the proposed dual-teacher distillation module to obtain the final discriminant results. The comprehensive experiments show that our IFAST can achieve state-of-the-art results on BNI-FAS, proving the effectiveness of the single-shot FAS based on binocular NIR images. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation