检索结果-内蒙古大学图书馆

MA-MNN: Multi-flow attentive memristive neural network for multi-task image restoration

Signal Processing: Image Communication 2025年 138卷

作者： He, Peng Zhang, Lin Yang, Yu Zhou, Yue Duan, Shukai Hu, Xiaofang College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Chongqing400715 China Ministry of Education China

Images taken in rainy, hazy, and low-light environments severely hinder the performance of outdoor computer vision systems. Most data-driven image restoration methods are task-specific and computationally intensive, whereas the capture and processing of degraded images occur largely in end-side devices with limited computing resources. Motivated by addressing the above issues, a novel software and hardware co-designed image restoration method named multi-flow attentive memristive neural network (MA-MNN) is proposed in this paper, which combines a deep learning algorithm and the nanoscale device memristor. The multi-level complementary spatial contextual information is exploited by the multi-flow aggregation block. The dense connection design is adopted to provide smooth transportation across units and alleviate the vanishing-gradient. The supervised calibration block is designed to facilitate achieving the dual-attention mechanism that helps the model identify and re-calibrate the transformed features. Besides, a hardware implementation scheme based on memristors is designed to provide low energy consumption solutions for embedded applications. Extensive experiments in image deraining, image dehazing and low-light image enhancement have shown that the proposed method is highly competitive with over 20 state-of-the-art methods. © 2025 Elsevier B.V.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Synergistic enhancement of memristive behavior and self-rectifying effect in MnO2 based memristor by ions doping method

引用

Applied Materials Today 2025年 44卷

作者： Yang, Bo Cao, Zelin Sun, Bai Gao, Kaikai Wang, Mengna Zhou, Guangdong Lv, Jian Luo, Sihai Chen, Xiaoliang Li, Xiangming Shao, Jinyou Frontier Institute of Science and Technology and Interdisciplinary Research Center of Frontier Science and Technology Xi'an Jiaotong University Shaanxi Xi'an710049 China Micro-and Nano-technology Research Center State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China College of Artificial Intelligence Brain-inspired Computing & Intelligent Control of Chongqing Key Lab Southwest University Chongqing400715 China

As one of the most promising candidates to replace the traditional von Neumann architecture, memristor shows considerable potential in neuromorphic computing, neural networks, brain-like chips, artificial intelligence, and information storage. However, its performance in terms of ultra-high stability, scalability, and extended switching windows has yet to be broken through, limiting its practical applications. In this work, it is investigated in detail the effect of Cu2+/Zn2+ ions doping on the memristive performance in the Ag/δ-MnO2/Ti devices with three different doping concentrations. We found that the optimal doping concentration can significantly improve the stability and resistance switching ratio of the device. Through first principles analysis, it is further confirmed that the main mechanism for the improvement in device switching ratio is the reduction of MnO bandgap caused by Cu2+/Zn2+ ions doping. Finally, we proposed that the formation of CuO/ZnO buffer layer through the interaction between Cu2+/Zn2+ ions and O2- ions is the key factor leading to the transition of threshold voltage from self-rectification to memristive behavior. Therefore, this work provides an in-deep understanding of the theory of metal ions doping in memristive device, which adds a new strategy to improve the memristive performance of the device in neuromorphic applications. © 2025 Elsevier Ltd

关键词： Electric rectifiers

来源：评论

学校读者我要写书评

暂无评论

An Image Denoising Method Based on Deep Residual GAN 4

An Image Denoising Method Based on Deep Residual GAN

引用

2020 4th International Workshop on Advanced Algorithms and control Engineering, IWAACE 2020

作者： Wang, Ziyuan Wang, Lidan Duan, Shukai Li, Yunfei Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China Schoolof Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificiall Intelligence Southwest University Chongqing400715 China Braininspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

As people come into contact with image data more often, high quality and clear images attract more attention. Many methods have been proposed to deal with image noise problem including deep learning (DL). However most of them is lack of capability when customers want more perceptual details of the image without information loss. In this paper, a deep residual network based on generative adversarial (GAN) network was proposed to complete the image denoising mission. Firstly, a generative-adversarial network structure based on residual blocks was designed. Secondly, a refined loss function was given to train the GAN network. The well designed loss function can help the generated image to be very close to the clear counterpart (ground truth) while enhancing more details in colours and brightness. Finally, extensive experiments show that our network is not only convincing for images denoising, but also effective for other image process tasks, such as image defogging, medical CT denoising etc., presenting impressive and competitive effects. © Published under licence by IOP Publishing Ltd.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

MC-CapsNet : Low-level Pooling and High-level Fusion of Multi-columns Capsule Network

MC-CapsNet : Low-level Pooling and High-level Fusion of Mult...

引用

2021 International Conference on Neuromorphic computing, ICNC 2021

作者： Li, Ke Duan, Shukai Wang, Lidan Wang, Yining Wang, Shu College of Artificial Intelligence Southwest University Brain-inspired Computing and Intelligent Control of Chongqing Key Lab National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing Brain Science Collaborative Innovation Center Chongqing China College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (纸本)9781665412872

Capsule network is a new type of neural network structure. The biggest feature of capsule network is 'vector in vector out', which replaces the previous 'scalar in scalar out'. The pristine capsule network completely discards the pooling layers and uses a convolutional kernel size of 9 × 9 to increase the perceptual field However, since the original capsule network has only two feature extraction layers, it cannot extract high level abstract features of objects, which are very important for image classification. Moreover, the original capsule network completely discards the use of pooling layers. Based on the above problems, we propose a multi-column capsule network (MC-CapsNet) with low-level pooling and high-level fusion. Unlike the traditional capsule network, MC-CapsNet has the following features: (a)MC-CapsNet consists of two columns of capsule network: the primary column of capsule network extracts high-level impalpable features;the other column of capsule network extracts subordinate shallow features (b)Pooling operation is added to the initial two convolutional layers of the two columns of capsule network (c)Using the high-level theoretical features extracted from the first capsule network to fuse features with the low-level surface layers extracted from the second capsule network to achieve feature complementarily (d)We add the elements of the digital capsule layers in the two-column capsule network to increase the probability of object features being detected by the capsule. The experimental results show that the classification accuracy of MC-CapsNet reaches 87.96% and 94.42% on the CIFAR10 and FashionMNIST datasets. © 2021 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

LAENet: Light-weight asymmetric encoder-decoder network for semantic segmentation

LAENet: Light-weight asymmetric encoder-decoder network for ...

引用

2021 International Conference on Artificial Intelligence and Industrial Technology Applications, AIITA 2021

作者： Hong, Liangyi Duan, Shukai Wang, Lidan Pan, Yongbin College of Electronic and Information Engineering Southwest University Chongqing China College of Artificial Intelligence Southwest University Chongqing China Brain-inspired Computing and Intelligent Control Chongqing Key Lab Chongqing China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing China Chongqing Brain Science Collaborative Innovation Center Chongqing China

Encode-decoder structure is used in deep learning for real-time dense segmentation task. On account of the limitation of calculation burden on mobile devices, we present a light-weight asymmetric encoder-decoder network in this paper, namely LAENet, which quickly and efficiently accomplish the task of real-time semantic segmentation. We employ an asymmetric convolution and group convolution structure combined with dilated convolution and dense connectivity to reduce computation cost and model size, which can guarantee adequate receptive field and enhance the model learning ability in encoder. On the other hand, feature pyramid networks (FPN) structure combine attention mechanism and ECRE block are utilized in the decoder to strike a balance between the network complexity and segmentation performance. Our approach achieves only have 0.84M parameters, and is able to reach 66 FPS in a single GTX 1080Ti GPU. Experiments on Cityscapes datasets demonstrate that superior performance of LAENet is better than the existing segmentation network, in terms of speed and accuracy trade-off without any post-processing. © Published under licence by IOP Publishing Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Car Plate Detection Based on Yolov3 5

Car Plate Detection Based on Yolov3

引用

2020 5th International Conference on intelligent computing and Signal Processing, ICSP 2020

作者： Shen, Siyuan Wang, Lidan Duan, Shukai He, Xin College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

An intelligent car plate detection method can make the travel more convenient and efficient. However, traditional methods are reasonably effective under the specific circumstances or strong assumptions only, and there are few databases for car plate detection. Therefore, a novel real-time car plate detection method based on improved Yolov3 has been proposed. In order to select the more precise number of candidate anchor boxed and aspect ratio dimensions, the K-Means algorithm is utilized. To solve the short of the available car plate database, a car plate database which has 6668 pictures has been established. As shown in the experimental results, the method which is proposed by this paper is better than original Yolov3. Thanks to the car plate database, the proposed method obtained better results even in the situation of inclination, too bright or too dark, different weather and so on. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Rain Removal from images based on Computer Vision and conditional Generative Adversarial Networks 3

Rain Removal from images based on Computer Vision and condit...

引用

2020 3rd International Conference on Advanced Algorithms and control Engineering, ICAACE 2020

作者： Li, Yunfei Wang, Lidan Chen, Taixing Wang, Ziyuan Duan, Shukai College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing 400715 China

In view of the quick development of modern computer technology, more pictures of natural scenes have been collected and analyzed for application in military fields, scientific research, and computer vision fields related to object detection. However, the sharpness of these pictures collected will be affected by rain and snow, which will reduce the visibility of things in the pictures. This will not only affect the viewing, but also affect scientific research fields such as autonomous driving and video surveillance. Therefore, the research on image rain removing is very practical. An improved algorithm model named pixel-GAN is proposed in this article, which based on conditional Generative Adversarial Networks (cGAN). This new method regards the problem of removing rain from specific images as the style conversion problem. What we improved is that a VGG-16 module is added to the original network to extract perceptual loss as a new part of the loss function. We show the excellent rain-removing ability of the improved algorithm and also illustrate the reason why we add the perceptual loss. Compared with other existing methods, there is no need to set a prior model, the training speed is faster and the proposed model finally generates higher quality pictures. © Published under licence by IOP Publishing Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust correlation filter that combined temporal regularization with spatial weight L1 constraint 4

Robust correlation filter that combined temporal regularizat...

引用

2020 4th International Workshop on Advanced Algorithms and control Engineering, IWAACE 2020

作者： He, Xin Duan, Shukai Wang, Lidan College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

The parameter optimization of the Object tracking algorithms has achieved excellent performance based on parameter regularization. Adaptive spatial regularization correlation filter can obtain the optimal weight coefficient for a specific target. Inspired by this, we propose a filter combined temporal regularity with spatial L1 regularization (LTASRCF). The time regularizer is used to remember the data of the previous frame to update the current target position. It performs well in the process of occlusion, deformation and motion blur. Meanwhile, L1 regularization of spatial weights reduces the computational complexity of the coefficients, and improves the robustness of the spatial weight matrix. We have conducted comparative experiments on the OTB-2015 dataset, and the proposed LTASRCF model ranks first among the five popular algorithms, which outperforms by 9.2% and 18.9% than KCF, respectively, and reaches real-time performance. © 2020 IOP Publishing Ltd. All rights reserved.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

An Attention-based Convolutional Neural Network for Melanoma Recognition 5

An Attention-based Convolutional Neural Network for Melanoma...

引用

2021 5th International Workshop on Advanced Algorithms and control Engineering, IWAACE 2021

作者： Chen, Qi Wang, Lidan Gan, Xiuling Duan, Shukai Southwest University College of Electronic and Information Engineering Chongqing400715 China Southwest University College of Artificial Intelligence Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

Early automatic and accurate melanoma recognition is an important method to reduce melanoma deaths. Existing methods are less sensitive to the position of the lesion areas. Network training may be affected by the uncorrelated noisy parts. In light of this circumstance, an end-to-end attention-based network AF-CNN for accurate melanoma recognition is proposed in this paper, which is mainly composed of pre-trained VGG19, attention blocks and a classification layer. Instead of treating each part of the input dermoscopy images equally, our AF-CNN model has strong discriminative ability to focus on the lesion areas. The AF-CNN was evaluated on the ISIC2017 dataset and concluded the proposed single model achieves the state-of-the-art result in melanoma recognition task. © Published under licence by IOP Publishing Ltd.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Chinese image caption of Inceptionv4 and double-layer GRUs based on attention mechanism 5

Chinese image caption of Inceptionv4 and double-layer GRUs b...

引用

2021 5th International Workshop on Advanced Algorithms and control Engineering, IWAACE 2021

作者： Pan, Yongbin Wang, Lidan Duan, Shukai Gan, Xiuling Hong, Liangyi College of Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificial Intelligence Southwest University Chongqing400715 China Brain-inspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

In recent years, there has been a wave of research on English image caption at home and abroad. However, due to the particularity of Chinese image caption task, the research on Chinese image caption has not made good progress. In order to solve this problem, a new Chinese image caption model is implemented. Firstly, the AI challenge dataset is enhanced, and then the Chinese text data of the dataset is preprocessed by Chinese word segmentation tool word2vec. Secondly, based on the encoder-decoder framework, the image visual features are extracted by Inceptionv4 network, the attention mechanism is incorporated in the process of feature extraction and the Chinese sentences are generated by double-layer GRUs network. In the process of training, Adam is used to optimize the algorithm. Finally, A GUI interface is designed to better show the experimental effect. Experiments show that the new Chinese image caption model can automatically generate more fluent and more accurate Chinese caption sentences, and the trained model has excellent performance in many evaluation indexes. © Published under licence by IOP Publishing Ltd.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：