检索结果-内蒙古大学图书馆

Mask R-CNN with R-D Net: A Detection and Segmentation Model for Early Gastric Cancer Gastroscopy Images

学校读者我要写书评

暂无评论

Mask R-CNN with R-D Net: A Detection and Segmentation Model ...

Electronic Information engineering and Computer science (EIECS), 2021 International Conference on

作者： Tao Liang Yi Lei Wenai Song Xue Sun Jun Du Qing Wang Li Zhao School of Software Engineering North University of China Taiyuan China Faculty of Information Technology Beijing University of Technology Beijing China VIP Department and Family Medicine Department Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Chinese Academy of Medical Sciences Beijing China Department of Pathology Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Chinese Academy of Medical Sciences Beijing China Pharmacovigilance Research Center for Information Technology and Data Science Cross-Strait Tsinghua Research Institute Xiamen China Department of Automation Tsinghua University Beijing China Department of Gastroenterology Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Chinese Academy of Medical Sciences Beijing China

Gastric cancer is one of the most common malignant tumors of the digestive system. Although gastroscopy can effectively detect early cancers, manual identification and diagnosis is time-consuming and laborious, and the false-negative rate is as high as 4.6-25.8%. Early gastric cancer lesion areas can be detected and segmented using deep learning techniques. We collected and organized 12665 eligible gastroscopy images, and cropped and expanded the original dataset after labeling by professional doctors, and finally obtained 19673 images for model training. We propose ResMSE Net and DWFF Net and apply these two networks to Mask R-CNN to obtain a new model: Mask R-CNN With R-D Net. On the same standard dataset, the mAP@[IoU=0.5] and ACC values of the Mask R-CNN With R-D Net model achieve respectively 45.37% and 67.74%, which are improved by 5.83% and 9.08%, respectively, compared with the original model. In our experiments, we found that Mask R-CNN With R-D Net is difficult to detect targets that are extremely similar to the background, which is the direction of our future work. Secondly, we hope to minimize the number of model parameters and make the model more lightweight under the premise of ensuring accuracy, so that the model can be embedded into gastroscopy detection equipment for real-time detection.

关键词：

Application of Improved Mask R-CNN Algorithm Based on Gastroscopic Image in Detection of Early Gastric Cancer

学校读者我要写书评

暂无评论

Application of Improved Mask R-CNN Algorithm Based on Gastro...

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Zhi-Heng Cui Qin-Yan Zhang Jing-Wei Zhang Xue Sun Qing Wang Yi Lei Lin Zang Li Zhao Ji-Jiang Yang School of Modern Posts Beijing University of Posts and Telecommunications Beijing China VIP Department and Family Medicine Department Chinese Academy of Medical Sciences Beijing Hospital Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine Beijing China Department of Automation Tsinghua University Beijing China Faculty of Information Technology School of Software Engineering Beijing University of Technology Beijing China Pharmacovigilance Research Center for information technology and Data Science Cross-strait Tsinghua Research Institute Xiamen China Department of Gastroenterology Beijing Hospital National Center of Gerontology Chinese Academy of Medical Sciences Beijing Hospital Institute of Geriatric Medicine Beijing China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

Gastroscopy is an important step in the diagnosis of early gastric cancer. However, because the morphological manifestations of early gastric cancer are not obvious, endoscopists need long-term specialized training and experience accumulation to correctly identify early cancer through magnification gastroscopy. In this paper, the data set of gastroscopy image is collected and enhanced, and target detection method is combined with gastroscopy image. The Mask R-CNN+BiFPN model was proposed to enhance the feature fusion and improve the detection effect of early gastric cancer lesions. Compared with Mask R-CNN, the improved Mask R-CNN model has better performance, with the sensitivity and specificity of 91.67% and 88.95% in accurately labeled gastroscopic datasets, respectively, showing a good segmentation effect for surface swelling lesions.

关键词： Training Image segmentation software algorithms Surface morphology Object detection Sensitivity and specificity Feature extraction

Towards automated metamorphic test identification for ocean system models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hiremath, Dilip Jagadeeshwarswamy Claus, Martin Hasselbring, Wilhelm Rath, Willi MarDATA - Helmholtz School for Marine Data Science GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel University Kiel Germany Software Engineering Group Computer Science Department Kiel University Kiel Germany Ocean Circulation and Climate Dynamics Department GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel University Kiel Germany Ocean Circulation and Climate Dynamics Department GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel Germany

Metamorphic testing seeks to verify software in the absence of test oracles. Our application domain is ocean system modeling, where test oracles rarely exist, but where symmetries of the simulated physical systems are known. The input data set is large owing to the requirements of the application domain. This paper presents work in progress for the automated generation of metamorphic test scenarios using machine learning. We extended our previously proposed method [1] to identify metamorphic relations with reduced computational complexity. Initially, we represent metamorphic relations as identity maps. We construct a cost function that minimizes for identifying a metamorphic relation orthogonal to previously found metamorphic relations and penalize for the identity map. A machine learning algorithm is used to identify all possible metamorphic relations minimizing the defined cost function. We propose applying dimensionality reduction techniques to identify attributes in the input which have high variance among the identified metamorphic relations. We apply mutation on these selected attributes to identify distinct metamorphic relations with reduced computational complexity. For experimental evaluation, we subject the two implementations of an ocean-modeling application to the proposed method to present the use of metamorphic relations to test the two implementations of this *** Codes J.2 © 2021, CC BY-SA.

关键词： Cost functions

A Distributed Privacy-Preserving Learning Dynamics in General Social Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tao, Youming Chen, Shuzhen Li, Feng Yu, Dongxiao Yu, Jiguo Sheng, Hao School of Computer Science and Technology Shandong University Qingdao266237 China Big Data Institute Qilu University of Technology Jinan250353 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

In this paper, we study a distributed privacy-preserving learning problem in social networks with general topology. The agents can communicate with each other over the network, which may result in privacy disclosure, since the trustworthiness of the agents cannot be guaranteed. Given a set of options which yield unknown stochastic rewards, each agent is required to learn the best one, aiming at maximizing the resulting expected average cumulative reward. To serve the above goal, we propose a four-staged distributed algorithm which efficiently exploits the collaboration among the agents while preserving the local privacy for each of them. In particular, our algorithm proceeds iteratively, and in every round, each agent i) randomly perturbs its adoption for the privacy-preserving purpose, ii) disseminates the perturbed adoption over the social network in a nearly uniform manner through random walking, iii) selects an option by referring to the perturbed suggestions received from its peers, and iv) decides whether or not to adopt the selected option as preference according to its latest reward feedback. Through solid theoretical analysis, we quantify the trade-off among the number of agents (or communication overhead), privacy preserving and learning utility. We also perform extensive simulations to verify the efficacy of our proposed social learning algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Generating Reliable Friends via Adversarial Training to Improve Social Recommendation

学校读者我要写书评

暂无评论

Generating Reliable Friends via Adversarial Training to Impr...

IEEE International Conference on data Mining (ICDM)

作者： Junliang Yu Min Gao Hongzhi Yin Jundong Li Chongming Gao Qinyong Wang School of Information Technology and Electrical Engineering The University of Queensland School of Big Data and Software Engineering Chongqing University Department of Electrical and Computer Engineering University of Virginia Department of Computer Science and School of Data Science University of Virginia

Most of the recent studies of social recommendation assume that people share similar preferences with their friends and the online social relations are helpful in improving traditional recommender systems. However, this assumption is often untenable as the online social networks are quite sparse and a majority of users only have a small number of friends. Besides, explicit friends may not share similar interests because of the randomness in the process of building social networks. Therefore, discovering a number of reliable friends for each user plays an important role in advancing social recommendation. Unlike other studies which focus on extracting valuable explicit social links, our work pays attention to identifying reliable friends in both the observed and unobserved social networks. Concretely, in this paper, we propose an end-to-end social recommendation framework based on Generative Adversarial Nets (GAN). The framework is composed of two blocks: a generator that is used to produce friends that can possibly enhance the social recommendation model, and a discriminator that is responsible for assessing these generated friends and ranking the items according to both the current user and her friends' preferences. With the competition between the generator and the discriminator, our framework can dynamically and adaptively generate reliable friends who can perfectly predict the current user' preference at a specific time. As a result, the sparsity and unreliability problems of explicit social relations can be mitigated and the social recommendation performance is significantly improved. Experimental studies on real-world datasets demonstrate the superiority of our framework and verify the positive effects of the generated reliable friends.

关键词：

Binary neural networks: A survey

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qin, Haotong Gong, Ruihao Liu, Xianglong Bai, Xiao Song, Jingkuan Sebe, Nicu State Key Lab of Software Development Environment Beihang University Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

Fine-grained iterative attention network for temporal language localization in videos

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qu, Xiaoye Tang, Pengwei Zou, Zhikang Cheng, Yu Dong, Jianfeng Zhou, Pan Xu, Zichuan School of Electronic Information and Communication Huazhong University of Science and Technology Huawei Tech. Hangzhou China School of Electronic Information and Communication Huazhong University of Science and Technology China Baidu Inc. China Microsoft Dynamics 365 AI Research RedmondWA United States School of Computer and Information Engineering Zhejiang Gongshang University China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Dalian University of Technology China

Temporal language localization in videos aims to ground one video segment in an untrimmed video based on a given sentence query. To tackle this task, designing an effective model to extract grounding information from both visual and textual modalities is crucial. However, most previous attempts in this field only focus on unidirectional interactions from video to query, which emphasizes which words to listen and attends to sentence information via vanilla soft attention, but clues from query-by-video interactions implying where to look are not taken into consideration. In this paper, we propose a Fine-grained Iterative Attention Network (FIAN) that consists of an iterative attention module for bilateral query-video in-formation extraction. Specifically, in the iterative attention module, each word in the query is first enhanced by attending to each frame in the video through fine-grained attention, then video iteratively attends to the integrated query. Finally, both video and query information is utilized to provide robust cross-modal representation for further moment localization. In addition, to better predict the target segment, we propose a content-oriented localization strategy instead of applying recent anchor-based localization. We evaluate the proposed method on three challenging public benchmarks: ActivityNet Captions, TACoS, and Charades-STA. FIAN significantly outperforms the state-of-the-art approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Vehicle re-identification with location and time stamps 32

学校读者我要写书评

暂无评论

Vehicle re-identification with location and time stamps

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019

作者： Lv, Kai Du, Heming Hou, Yunzhong Deng, Weijian Sheng, Hao Jiao, Jianbin Zheng, Liang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University University of Chinese Academy of Sciences Australian National University

ISBN: (纸本)9781728125060

This paper focuses on the problem of vehicle re-identification (Re-ID). In our attempt, we propose a re-identification framework by exploiting vehicle location and time stamps. The location and time information have the potential to cover the shortage of appearance-based feature representations. First, we introduce an ensemble technique to combine the informative cues of multiple Re-ID models effectively. To further improve the accuracy, we then build up a system to acquire the vehicle location and time stamps. Specifically, we utilize the detected results to obtain the needed information. With the help of the proposed system, we can remove irrelevant images from a given ranking list. Our system finished 3rd place in the 2019 AI-City challenge for city-scale multi-camera vehicle re-identification. © 2019 IEEE Computer Society. All rights reserved.

关键词： Vehicles

Harmonia: A high throughput B+tree for GPUs 19

学校读者我要写书评

暂无评论

Harmonia: A high throughput B+tree for GPUs

24th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2019

作者： Yan, Zhaofeng Lin, Yuzhe Peng, Lu Zhang, Weihua Software School Fudan University China Shanghai Key Laboratory of Data Science Fudan University China Shanghai Institute of Intelligent Electronics and Systems Shanghai China Division of Electrical and Computer Engineering Louisiana State University United States

ISBN: (纸本)9781450362252

B+tree is one of the most important data structures and has been widely used in different fields. With the increase of concurrent queries and data-scale in storage, designing an eficient B+tree structure has become critical. Due to abundant computation resources, GPUs provide potential opportunities to achieve high query throughput for B+tree. However, prior methods cannot achieve satisfactory performance results due to low resource utilization and poor memory performance. In this paper, we first identify the gaps between B+tree and GPUs. Concurrent B+tree queries involve many global memory accesses and different divergences, which mismatch with GPU features. Based on this observation, we propose Harmonia, a novel B+tree structure to bridge the gap. In Harmonia, a B+tree structure is divided into a key region and a child region. The key region stores the nodes with its keys in a breadth-first order. The child region is organized as a prefix-sum array, which only stores each node's first child index in the key region. Since the prefix-sum child region is small and the children's index can be retrieved through index computations, most of it can be stored in on-chip caches, which can achieve good cache locality. To make it more eficient, Harmonia also includes two optimizations: partially-sorted aggregation and narrowed thread-group traversal, which can mitigate memory and warp divergence and improve resource utilization. Evaluations on a TITAN V GPU show that Harmonia can achieve up to 3.6 billion queries per second, which is about 3.4X faster than that of HB+Tree [39], a recent state-of-the-art GPU solution. © 2019 Association for Computing Machinery.

关键词： Trees (mathematics)