检索结果-内蒙古大学图书馆

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Size-invariance matters: rethinking metrics and losses for imbalanced multi-object salient object detection 24

学校读者我要写书评

暂无评论

Size-invariance matters: rethinking metrics and losses for i...

Proceedings of the 41st International Conference on Machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

A deep learning system for predicting time to progression of diabetic retinopathy

学校读者我要写书评

暂无评论

NATURE MEDICINE 2024年第2期30卷 358-359页

作者： [Anonymous] Shanghai Belt and Road International Joint Laboratory for Intelligent Prevention and Treatment of Metabolic Disorders Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Huadong Sanatorium Wuxi China Department of Ophthalmology Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong China Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Department of Ophthalmology Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing China Medical Records and Statistics Office Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Geriatrics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Tech

We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.

关键词： Diabetes complications Machine learning Predictive markers

PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cong, Runmin Yang, Wenyu Zhang, Wei Li, Chongyi Guo, Chun-Le Huang, Qingming Kwong, Sam Institute of Information Science Beijing Jiaotong University Beijing100044 China School of Control Science and Engineering Shandong University Jinan250061 China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan250061 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China College of Computer Science Nankai University Tianjin300350 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China Department of Computer Science City University of Hong Kong Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement subnetwork (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics. The code and results can be found from the link of https://***/proj_***. © 2023, CC BY-NC-SA.

关键词： Discriminators

Landscape of big medical data: A pragmatic survey on prioritized tasks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Zhifei Gao, Wanling Zhang, Fan Huang, Yunyou Dai, Shaopeng Fan, Fanda Zhan, Jianfeng Du, Mengjia Yin, Silin Xiong, Longxin Du, Juan Cheng, Yumei Zhou, Xiexuan Ren, Rui Wang, Lei Ye, Hainan Department of Physiology and Pathophysiology Capital Medical University State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Nanchang First Hospital Neonatal Center Beijing Children's Hospital Affiliated to Capital Medical University Beijing Obstetrics and Gynecology Hospital Affiliated to Capital Medical University Beijing Academy of Frontier Sciences and Technology

Big medical data poses great challenges to life scientists, clinicians, computer scientists, and engineers. In this paper, a group of life scientists, clinicians, computer scientists and engineers sit together to discuss several fundamental issues. First, what are the unique characteristics of big medical data different from those of the other domains? Second, what are the prioritized tasks in clinician research and practices utilizing big medical data? And do we have enough publicly available data sets for performing those tasks? Third, do the state-of-the-practice and state-of-the-art algorithms perform good jobs? Fourth, are there any benchmarks for measuring algorithms and systems for big medical data? Fifth, what are the performance gaps of state-of-the-practice and state-of-the-art systems handling big medical data currently or in future? Finally but not least, are we, life scientists, clinicians, computer scientists and engineers, ready for working together? We believe answering the above issues will help define and shape the landscape of big medical data. Copyright © 2019, The Authors. All rights reserved.

关键词： computer aided diagnosis

Improved adaptive buffer replacement algorithm used for second level buffer

学校读者我要写书评

暂无评论

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2007年第8期44卷 1331-1338页

作者： Sun, Guozhong Yuan, Qingbo Chen, Mingyu Fan, Jianping National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Acad. of Sci. Beijing 100080 China Graduate University Chinese Acad. of Sci. Beijing 100049 China Key Laboratory of Computer System and Architecture Chinese Acad. of Sci. Beijing 100080 China Institute of Computing Technology Chinese Acad. of Sci. Beijing 100080 China

In a cluster or a database server system, the performance of some data intensive applications will be degraded much because of the limited local memory and large amount of interactions with slow disk. In high speed network, utilizing remote memory of other nodes or customized memory server to be as second level buffer can decrease access numbers to disks and benefit application performance. With second level buffer mode, this paper made some improvements for a recently proposed buffer cache replacement algorithm-LIRS, and brings forward an adaptive algorithm-LIRS-A. LIRS-A can adaptively adjust itself according to application characteristic, thus the problem of not suiting for time locality of LIRS is avoided. In TPC-H benchmarks, LIRS-A could improve hit rate over LIRS by 7.2% at most. In a Groupby query with network stream analyzing database, LIRS-A could improve hit rate over LIRS by 31.2% at most. When compared with other algorithms, LIRS-A also show similar or better performance.

关键词： Buffer storage

High Quality Global Routing Algorithm Based on Multi-Stage Optimization

学校读者我要写书评

暂无评论

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of computer-Aided Design and computer Graphics 2024年第4期36卷 607-614页

作者： Genggeng, Liu Zhenyu, Pei Ning, Xu College of Computer and Data Science Fuzhou University Fuzhou350116 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Information Engineering Wuhan University of Technology Wuhan430070 China

Global routing is a crucial step in VLSI physical design. To address the problems that the low utilization rate of capacity and easy to fall into local optimum in the existing global routing algorithms, a high-quality global routing algorithm based on multi-stage optimization is proposed. First, the virtual capacity dynamic adjustment strategy is introduced in the pre-connection stage and the routing reorganization stage to improve the utilization rate of capacity. Then, in the routing reorganization stage, the routing subarea adaptive expansion strategy is proposed to narrow the search space and improve the routing efficiency. Finally, the A* algorithm heuristic search is combined with the global search capability of the particle swarm algorithm to avoid the algorithm to choose the shortest path in the routing process, and thus avoid the algorithm to fall into the local optimum. Experimental results comparing with existing global routing algorithms on ISPD benchmark circuits show that the routing results of proposed algorithm reduce the wirelength by 6.0% to 22.8%. © 2024 institute of computing technology. All rights reserved.

关键词： Routing algorithms

Dental Detection and Classification of YOLOv3-SPP based on Convolutional Block Attention Module

学校读者我要写书评

暂无评论

Dental Detection and Classification of YOLOv3-SPP based on C...

International Conference on computer and Communications (ICCC)

作者： Ning Li Ruifeng Guo Xiaozhou Liu Lin Wu Hongliang Wang Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Shenyang China Liaoning Provience Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Liaoning Provincial Key Laboratory of Oral Diseases School and Hospital of Stomatology China Medical University Shenyang China

The purpose of this research paper is to implement the tooth target detection task by deep convolutional neural networks. In order to solve the problems of low accuracy of target detection due to the high similarity between teeth and complex tooth textures, an improved tooth detection method with YOLOv3-SPP model is proposed in this paper. This method incorporates the convolutional block attention module (CBAM) in the YOLOv3-SPP algorithm framework, and improves the performance of the network features by adding the channel attention mechanism and spatial attention mechanism to the feature extraction network to enhance the saliency of the tooth target region in the image. Secondly, CIoU border regression loss is introduced to improve the localization accuracy. In addition, a Non-maximum suppression (NMS) method is used to solve the candidate frame overlap problem. Through experiments, it is shown that the mAP of the modified YOLOv3-SPP target detection model is improved to 86.8 percent, which indicates that the improved model can be applied to the detection of teeth.

关键词： Location awareness Training Teeth Object detection Feature extraction Dentistry Classification algorithms

Extending the limit of molecular dynamics with ab initio accuracy to 10 billion atoms

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Zhuoqiang Lu, Denghui Yan, Yujin Hu, Siyu Liu, Rongrong Tan, Guangming Sun, Ninghui Jiang, Wanrun Liu, Lijun Chen, Yixiao Zhang, Linfeng Chen, Mohan Wang, Han Jia, Weile Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Architecture ICT Chinese Academy of Sciences Beijing China HEDPS CAPT College of Engineering Peking University Beijing China AI for Science Institute Beijing China Osaka University Osaka Japan Princeton University Princeton United States DP Technology Beijing China Laboratory of Computational Physics Institute of Applied Physics and Computational Mathematics Beijing China

High-performance computing, together with a neural network model trained from data generated with first-principles methods, has greatly boosted applications of ab initio molecular dynamics in terms of spatial and temporal scales on modern supercomputers. Previous state-of-the-art can achieve 1 − 2 nanoseconds molecular dynamics simulation per day for 100-million atoms on the entire Summit supercomputer. In this paper, we have significantly reduced the memory footprint and computational time by a comprehensive approach with both algorithmic and system innovations. The neural network model is compressed by model tabulation, kernel fusion, and redundancy removal. Then optimizations such as acceleration of customized kernel, tabulation of activation function, MPI+OpenMP parallelization are implemented on GPU and ARM architectures. Testing results of the copper system show that the optimized code can scale up to the entire machine of both Fugaku and Summit, and the corresponding system size can be extended by a factor of 134 to an © 2022, CC BY-NC-SA.

关键词： Supercomputers