检索结果-南通市图书馆

Mask Distillation Network for Conjunctival Hyperemia Severity Classification

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2023年第6期20卷 909-922页

作者： Mingchao Li Kun Huang Xiao Ma Yuexuan Wang Wen Fan Qiang Chen School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing210094China Department of Ophthalmology The First Affiliated Hospital with Nanjing Medical UniversityNanjing210029China

To achieve automatic,fast and accurate severity classification of bulbar conjunctival hyperemia severity,we proposed a novel prior knowledge-based framework called mask distillation network(MDN).The proposed MDN consists of a segmentation network and a classification network with teacher-student branches.The segmentation network is used to generate a bulbar conjunctival mask and the classification network divides the severity of bulbar conjunctival hyperemia into four grades.In the classification network,we feed the original image and the image with the bulbar conjunctival mask into the student and teacher branches respectively,and an attention consistency loss and a classification consistency loss are used to keep a similar learning mode for these two branches.This design of“different input but same output”,named mask distillation(MD),aims to introduce the regional prior knowledge that“bulbar conjunctival hyperemia severity classification is only related to the bulbar conjunctiva region”.Extensive experiments on 5117 anterior segment images have proven the effectiveness of mask distillation technology:1)The accuracy of the MDN student branch is 3.5%higher than that of a single optimal baseline network and 2%higher than that of the baseline network combination.2)In the test phase,only the student branch is needed,and no additional segmentation network is required.The framework only takes 0.003 s to classify a single image,achieving the fastest speed in all the methods we compared.3)Compared with a single baseline network,the attention of both teacher and student branches in the MDN has been intuitively improved.

关键词： Mask distillation(MD) conjunctiva hyperemia attention mechanism severity classification deep learning

A Pixel–Channel Hybrid attention Model for Image Processing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2022年第5期27卷 804-816页

作者： Qiang Hua Liyou Chen Pan Li Shipeng Zhao Yan Li College of Mathematics and Information Science Hebei UniversityBaoding 071002China Research Center for Applied Mathematics and Interdisciplinary Sciences Beijing Normal UniversityZhuhai 519087China

In the field of image processing,better results can often be achieved through the deepening of neural network layers involving considerably more parameters.In image classification,improving classification accuracy without introducing too many parameters remains a challenge.As for image conversion,the use of the conversion model of the generative adversarial network often produces semantic artifacts,resulting in images with lower quality.Thus,to address the above problems,a new type of attention module is proposed in this paper for the first time.This proposed approach uses the pixel-channel hybrid attention(PCHA) mechanism,which combines the attention information of the pixel and channel domains.The comparative results of using different attention modules on multiple-image data verify the superiority of the PCHA module in performing classification tasks.For image conversion,we propose a skip structure(S-PCHA model) in the up-and down-sampling processes based on the PCHA model.The proposed model can help the algorithm identify the most distinctive semantic object in a given image,as this structure effectively realizes the intercommunication of encoder and decoder information.Furthermore,the results showed that the attention model could establish a more realistic mapping from the source domain to the target domain in the image conversion algorithm,thus improving the quality of the image generated by the conversion model.

关键词： deep learning attention mechanism image classification image processing convolutional neural networks

AOGAN:A generative adversarial network for screen space ambient occlusion

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第3期8卷 483-494页

作者： Lei Ren Ying Song Zhejiang Sci-Tech University Hangzhou 310018China 2011 Collaborative Innovation Center for Garment Personal Customization of Zhejiang Province China Key Lab of Silk and Culture Heritage and Products Design Digital Technology Ministry of Culture and TourismChina

Ambient occlusion(AO)is a widely-used real-time rendering technique which estimates light intensity on visible scene surfaces.Recently,a number of learning-based AO approaches have been proposed,which bring a new angle to solving screen space shading via a unified learning framework with competitive quality and speed.However,most such methods have high error for complex scenes or tend to ignore details.We propose an end-to-end generative adversarial network for the production of realistic AO,and explore the importance of perceptual loss in the generative model to AO accuracy.An attention mechanism is also described to improve the accuracy of details,whose effectiveness is demonstrated on a wide variety of scenes.

关键词： ambient occlusion(AO) attention mechanism generative adversarial network(GAN) perceptual loss

Material decomposition of spectral CT images via attention-based global convolutional generative adversarial network

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2023年第3期34卷 143-153页

作者： Xiaodong Guo Peng He Xiaojie Lv Xuezhi Ren Yonghui Li Yuanfeng Liu Xiaohua Lei Peng Feng Hongming Shan The Key Lab of Optoelectronic Technology and Systems of the Education Ministry of China Chongqing UniversityChongqing 400044China Department of Vascular and Endovascular Surgery First Affiliated Hospital of Zhengzhou UniversityZhengzhou 450003China Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China

Spectral computed tomography(CT)based on photon counting detectors can resolve the energy of every single photon interacting with the sensor layer and be used to analyze material attenuation information under different energy ranges,which can be helpful for material decomposition studies.However,there is a considerable amount of inherent quantum noise in narrow energy bins,resulting in a low signal-to-noise ratio,which can consequently affect the material decomposition performance in the image domain.Deep learning technology is currently widely used in medical image segmentation,denoising,and recognition.In order to improve the results of material decomposition,we propose an attention-based global convolutional generative adversarial network(AGC-GAN)to decompose different materials for spectral CT.Specifically,our network is a global convolutional neural network based on an attention mechanism that is combined with a generative adversarial network.The global convolutional network based on the attention mechanism is used as the generator,and a patchGAN discriminant network is used as the discriminator.Meanwhile,a clinical spectral CT image dataset is used to verify the feasibility of our proposed approach.Extensive experimental results demonstrate that AGC-GAN achieves a better material decomposition performance than vanilla U-Net,fully convolutional network,and fully convolutional denseNet.Remarkably,the mean intersection over union,structural similarity,mean precision,PAcc,and mean F1-score of our method reach up to 87.31%,94.83%,93.22%,97.39%,and 93.05%,respectively.

关键词： Photon-counting CT Material decomposition attention mechanism GAN

Neural Emotion Detection via Personal Attributes

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2022年第5期37卷 1146-1160页

作者：周夏冰王中卿梁兴伟张民周国栋 School of Computer Science and Technology Soochow UniversitySuzhou 215006China Konka AIOT Research Laboratory Konka Group Company LimitedShenzhen 518053China

There has been a recent line of work to automatically detect the emotions of posts in social media.In literature,studies treat posts independently and detect their emotions separately.Different from previous studies,we explore the dependence among relevant posts via authors'backgrounds,since the authors with similar backgrounds,e.g.,"gender","location",tend to express similar emotions.However,personal attributes are not easy to obtain in most social media websites.Accordingly,we propose two approaches to determine personal attributes and capture personal attributes between different posts for emotion detection:the Joint Model with Personal attention mechanism(JPA)model is used to detect emotion and personal attributes jointly,and capture the attributes-aware words to connect similar people;the Neural Personal Discrimination(NPD)model is employed to determine the personal attributes from posts and connect the relevant posts with similar attributes for emotion detection.Experimental results show the usefulness of personal attributes in emotion detection,and the effectiveness of the proposed JPA and NPD approaches in capturing personal attributes over the state-of-the-art statistic and neural models.

关键词： emotion detection adversarial network attention mechanism personal attribute

An attention-embedded GAN for SVBRDF recovery from a single image

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第3期9卷 551-561页

作者： Zeqi Shi Xiangyu Lin Ying Song Zhejiang Sci-Tech University 2011 Collaborative Innovation Center for Garment Personal Customization of Zhejiang ProvinceHangzhou 310018China.

Learning-based approaches have made substantial progress in capturing spatially-varying bidirectional reflectance distribution functions(SVBRDFs)from a single image with unknown lighting and geometry.However,most existing networks only consider per-pixel losses which limit their capability to recover local features such as smooth glossy regions.A few generative adversarial networks use multiple discriminators for different parameter maps,increasing network complexity.We present a novel end-to-end generative adversarial network(GAN)to recover appearance from a single picture of a nearly-flat surface lit by flash.We use a single unified adversarial framework for each parameter map.An attention module guides the network to focus on details of the maps.Furthermore,the SVBRDF map loss is combined to prevent paying excess attention to specular highlights.We demonstrate and evaluate our method on both public datasets and real data.Quantitative analysis and visual comparisons indicate that our method achieves better results than the state-of-the-art in most cases.

关键词： spatially-varying bidirectional reflectance distribution function(SVBRDF) appearance capture generative adversarial network(GAN) attention mechanism

Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute attention Localization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2022年第2期19卷 153-168页

作者： Wei-Chen Chen Xin-Yi Yu Lin-Lin Ou College of Information Engineering Zhejiang University of TechnologyHangzhou 310023China

Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention(VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets(richly annotated pedestrian(RAP), annotated pedestrian v2(RAPv2), and PA-100 K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.

关键词： Pedestrian attribute recognition surveillance scenarios view-attribute attention mechanism localization

A new target tracking filter based on deep learning

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第5期35卷 11-24页

作者： Yaqi CUI You HE Tiantian TANG Yu LIU Naval Aviation University Yantai 264001China

At present,current filters can basically solve the filtering problem in target tracking,but there are still many problems such as too many filtering variants,too many filtering forms,loosely coupled with the target motion model,and so on.To solve the above problems,we carry out crossapplication research of artificial intelligence theory and methods in the field of tracking filters.We firstly analyze the computation graphs of typical a-βand Kalman.Through analysis,it is concluded that a-βand Kalman have the same computation structures analogous to a typical recurrent neural network and can be considered as a kind of recurrent neural network with constrained weights.Then,given this and considering that a recurrent neural network has the recognition capability for target motion patterns,a new filter is developed in a unified neural network architecture and specifically constructed using feedforward neural network,recurrent neural network,and attention mechanism.And the unified tracking filter proposed in this paper can generate three aspects of unity:a unified target motion model,an adaptive filter method,and an overall track filtering framework.Finally,Simulation results show that the proposed filter is effective and useful,of which the overall performance is superior to those of compared filters.

关键词： attention mechanism Feedforward neural network Interactive multiple model Recurrent neural network Tracking filter

Accurate Robotic Grasp Detection with Angular Label Smoothing

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2023年第5期38卷 1149-1161页

作者：石敏路昊李兆歆朱登明王兆其 School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Grasp detection is a visual recognition task where the robot makes use of its sensors to detect graspable objects in its environment.Despite the steady progress in robotic grasping,it is still difficult to achieve both real-time and high accuracy grasping detection.In this paper,we propose a real-time robotic grasp detection method,which can accurately predict potential grasp for parallel-plate robotic grippers using RGB images.Our work employs an end-to-end convolutional neural network which consists of a feature descriptor and a grasp detector.And for the first time,we add an attention mechanism to the grasp detection task,which enables the network to focus on grasp regions rather than background.Specifically,we present an angular label smoothing strategy in our grasp detection method to enhance the fault tolerance of the network.We quantitatively and qualitatively evaluate our grasp detection method from different aspects on the public Cornell dataset and Jacquard dataset.Extensive experiments demonstrate that our grasp detection method achieves superior performance to the state-of-the-art methods.In particular,our grasp detection method ranked first on both the Cornell dataset and the Jacquard dataset,giving rise to the accuracy of 98.9%and 95.6%,respectively at realtime calculation speed.

关键词： robotic grasp detection attention mechanism angular label smoothing anchor box deep learning