检索结果-内蒙古大学图书馆

A3Net: Adversarial-and-attention network for machine reading comprehension

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wang, Jiuniu Fu, Xingyu Xu, Guangluan Wu, Yirong Chen, Ziyan Wei, Yang Jin, Li Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics CAS Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

In this paper, we introduce Adversarial-and-attention Network (A3Net) for Machine Reading Comprehension. This model extends existing approaches from two perspectives. First, adversarial training is applied to several target variables within the model, rather than only to the inputs or embeddings. We control the norm of adversarial perturbations according to the norm of original target variables, so that we can jointly add perturbations to several target variables during training. As an effective regularization method, adversarial training improves robustness and generalization of our model. Second, we propose a multi-layer attention network utilizing three kinds of high-efficiency attention mechanisms. Multi-layer attention conducts interaction between question and passage within each layer, which contributes to reasonable representation and understanding of the model. Combining these two contributions, we enhance the diversity of dataset and the information extracting ability of the model at the same time. Meanwhile, we construct A3Net for the WebQA dataset. Results show that our model outperforms the state-of-the-art models (improving Fuzzy Score from 73.50% to 77.0%). Copyright © 2018, The Authors. All rights reserved.

关键词： Network layers

DENSE-ADD NET: AN NOVEL CONVOLUTIONAL NEURAL NETWORK FOR REMOTE SENSING IMAGE INPAINTING

学校读者我要写书评

暂无评论

DENSE-ADD NET: AN NOVEL CONVOLUTIONAL NEURAL NETWORK FOR REM...

IEEE International geoscience and Remote Sensing Symposium

作者： Daoyu Lin Guangluan Xu Yang Wang Xian Sun Kun Fu School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

Through the recent performance of convolutional neural networks in image processing tasks, we propose a deep fully convolutional network for remote sensing image inpainting. The proposed Dense-Add Net (Dense-Add Network) can alleviate the vanishing-gradient problem, strengthen feature reuse, and substantially reduce the memory usage. We apply residual learning to learn the mappings from corrupted image to recovered image directly;it will back-propagate gradient to the bottom layers and accelerate the training process. We train the proposed Dense-Add Net with a robust Charbonnier loss function which can achieve high-quality reconstruction. The experimental verify the efficacy of our proposed Dense-Add Net.

关键词： Remote sensing Training Acceleration Image reconstruction Painting Convolution Interpolation

A HYBRID NEURAL NETWORK FOR CHROMA INTRA PREDICTION

学校读者我要写书评

暂无评论

A HYBRID NEURAL NETWORK FOR CHROMA INTRA PREDICTION

IEEE International Conference on Image processing

作者： Yue Li Li Li Zhu Li Jianchao Yang Ning Xu Dong Liu Houqiang Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China University of Missouri Kansas City MO USA Snapchat Inc. CA USA

For chroma intra prediction, previous methods exemplified by the Linear Model method (LM) usually assume a linear correlation between the luma and chroma components in a coding block. This assumption is inaccurate for complex image content or large blocks, and restricts the prediction accuracy. In this paper, we propose a chroma intra prediction method by exploiting both spatial and cross-channel correlations using a hybrid neural network. Specifically, we utilize a convolutional neural network to extract features from the reconstructed luma samples of the current block, as well as utilize a fully connected network to extract features from the neighboring reconstructed luma and chroma samples. The extracted twofold features are then fused to predict the chroma samples-Cb and Cr simultaneously. The proposed chroma intra prediction method is integrated into HEVC. Preliminary results show that, compared with HEVC plus LM, the proposed method achieves on average 0.2%, 3.1% and 2.0% BD-rate reduction on Y, Cb and Cr components, respectively, under All-Intra configuration.

关键词： Feature extraction Neural networks Kernel Correlation Image reconstruction Encoding Prediction methods

Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Xue Sun, Hao Fu, Kun Yang, Jirui Sun, Xian Yan, Menglong Guo, Zhi Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing

Ship detection has been playing a significant role in the field of remote sensing for a long time but it is still full of challenges. The main limitations of traditional ship detection methods usually lie in the complexity of application scenarios, the difficulty of intensive object detection and the redundancy of detection region. In order to solve such problems above, we propose a framework called Rotation Dense Feature Pyramid Networks (R-DFPN) which can effectively detect ship in different scenes including ocean and port. Specifically, we put forward the Dense Feature Pyramid Network (DFPN), which is aimed at solving the problem resulted from the narrow width of the ship. Compared with previous multi-scale detectors such as Feature Pyramid Network (FPN), DFPN builds the high-level semantic feature-maps for all scales by means of dense connections, through which enhances the feature propagation and encourages the feature reuse. Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall. Furthermore, we also propose multi-scale ROI Align for the purpose of maintaining the completeness of semantic and spatial information. Experiments based on remote sensing images from Google Earth for ship detection show that our detection method based on RDFPN representation has a state-of-The-Art performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Remote sensing

HIGH RESOLUTION SAR IMAGE CLASSIFICATION WITH DEEPER CONVOLUTIONAL NEURAL NETWORK

学校读者我要写书评

暂无评论

HIGH RESOLUTION SAR IMAGE CLASSIFICATION WITH DEEPER CONVOLU...

IEEE International geoscience and Remote Sensing Symposium

作者： Yue Zhang Xian Sun Hao Sun Zequn Zhang Wenhui Diao Kun Fu Key Laboratory of Spatial Information Processing and Application System Technology Chinese Academy of Sciences Beijing China Institute of Electronic Chinese Academy of Sciences Beijing China

Deeper architectures are proven to be beneficial for the classification performance obviously in computer vision field. Inspired by this, deep CNNs are expected to make progress in the SAR target classification problem as well. However, it is hard to train deeper CNNs for SAR images. Such CNNs have millions of parameters to be determined in the network (for example the VGGNet has more than 130 million parameters), hence large-scale dataset is indispensable when training a deep CNN. But there is no large-scale annotated SAR target dataset, and data acquisition and annotation is much more costly for SAR images. With inadequate data, the network is easy to be overfitting. Several methods based on deep learning have been proposed for SAR image classifications, but they cannot get rid of the aforementioned data limitation of labelled SAR images. To solve this problem, this paper proposes a microarchitecture called CompressUnit (CU). With CU, we design a deeper CNN. Compared with the network with the fewest parameters for SAR image classification in literature so far, our network is 2X deeper with only about 10% of parameters. In this way, we get a deeper network with much fewer parameters. This network is easier to be trained with limited SAR data and is more likely to get rid of overfitting.

关键词： Deeper CNN SAR images CompressUnit

Automatic coregistration for multiview SAR images in urban areas

学校读者我要写书评

暂无评论

Automatic coregistration for multiview SAR images in urban a...

ISPRS geospatial Week 2017

作者： Xiang, Yuming Kang, Wenchao Wang, Feng You, Hongjian Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Due to the high resolution property and the side-looking mechanism of SAR sensors, complex buildings structures make the registration of SAR images in urban areas becomes very hard. In order to solve the problem, an automatic and robust coregistration approach for multiview high resolution SAR images is proposed in the paper, which consists of three main modules. First, both the reference image and the sensed image are segmented into two parts, urban areas and nonurban areas. Urban areas caused by double or multiple scattering in a SAR image have a tendency to show higher local mean and local variance values compared with general homogeneous regions due to the complex structural information. Based on this criterion, building areas are extracted. After obtaining the target regions, L-shape structures are detected using the SAR phase congruency model and Hough transform. The double bounce scatterings formed by wall and ground are shown as strong L- or T-shapes, which are usually taken as the most reliable indicator for building detection. According to the assumption that buildings are rectangular and flat models, planimetric buildings are delineated using the L-shapes, then the reconstructed target areas are obtained. For the orignal areas and the reconstructed target areas, the SAR-SIFT matching algorithm is implemented. Finally, correct corresponding points are extracted by the fast sample consensus (FSC) and the transformation model is also derived. The experimental results on a pair of multiview TerraSAR images with 1-m resolution show that the proposed approach gives a robust and precise registration performance, compared with the orignal SAR-SIFT method.

关键词： Synthetic aperture radar

A novel and fast corner detection method for SAR imagery

学校读者我要写书评

暂无评论

A novel and fast corner detection method for SAR imagery

ISPRS geospatial Week 2017

作者： Jiao, Niangang Kang, Wenchao Xiang, Yuming You, Hongjian Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Corners play an important role on image processing, while it is difficult to detect reliable and repeatable corners in SAR images due to the complex property of SAR sensors. In this paper, we propose a fast and novel corner detection method for SAR imagery. First, a local processing window is constructed for each point. We use the local mean of a 3 × 3 mask to represent a single point, which is weighted by a Gaussian template. Then the candidate point is compared with 16 surrounding points in the processing window. Considering the multiplicative property of speckle noise, the similarity measure between the center point and the surrounding points is calculated by the ratio of their local means. If there exist more than M continuous points are different from the center point, then the candidate point is labelled as a corner point. Finally, a selection strategy is implemented by ranking the corner score and employing the non-maxima suppression method. Extreme situations such as isolated bright points are also removed. Experimental results on both simulated and real-world SAR images show that the proposed detector has a high repeatability and a low localization error, compared with other state-of-the-art detectors.

关键词： Synthetic aperture radar

Wider channel attention network for remote sensing image super-resolution

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Gu, Jun Xu, Guangluan Zhang, Yue Sun, Xian Wen, Ran Wang, Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Recently, deep convolutional neural networks (CNNs) have obtained promising results in image processing tasks including super-resolution (SR). However, most CNN-based SR methods treat low-resolution (LR) inputs and features equally across channels, rarely notice the loss of information flow caused by the activation function and fail to leverage the representation ability of CNNs. In this letter, we propose a novel single-image super-resolution (SISR) algorithm named Wider Channel Attention Network (WCAN) for remote sensing images. Firstly, the channel attention mechanism is used to adaptively recalibrate the importance of each channel at the middle of the wider attention block (WAB). Secondly, we propose the Local Memory Connection (LMC) to enhance the information flow. Finally, the features within each WAB are fused to take advantage of the network’s representation capability and further improve information and gradient flow. Analytic experiments on a public remote sensing data set (UC Merced) show that our WCAN achieves better accuracy and visual improvements against most state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Image fusion

Position detection and direction prediction for arbitrary-oriented ships via multiscale rotation region convolutional neural network

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Fu, Kun Guo, Zhi Yan, Menglong Sun, Xian Sun, Hao Yang, Xue Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

—Ship detection is of great importance and full of challenges in the field of remote sensing. The complexity of application scenarios, the redundancy of detection region, and the difficulty of dense ship detection are all the main obstacles that limit the successful operation of traditional methods in ship detection. In this paper, we propose a brand new detection model based on multiscale rotational region convolutional neural network to solve the problems above. This model is mainly consist of five consecutive parts: Dense Feature Pyramid Network (DFPN), adaptive region of interest (ROI) Align, rotational bounding box regression, prow direction prediction and rotational nonmaximum suppression (R-NMS). First of all, the low-level location information and high-level semantic information are fully utilized through multiscale feature networks. Then, we design adaptive ROI Align to obtain high quality proposals which remain complete spatial and semantic information. Unlike most previous approaches, the prediction obtained by our method is the minimum bounding rectangle of the object with less redundant regions. Therefore, rotational region detection framework is more suitable to detect the dense object than traditional detection model. Additionally, we can find the berthing and sailing direction of ship through prediction. A detailed evaluation based on SRSS and DOTA dataset for rotation detection shows that our detection method has a competitive performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Remote sensing