检索结果-内蒙古大学图书馆

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

Fractional Order Differential Evolution

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Wang, Kaiyu Gao, Shangce Zhou, MengChu Zhan, Zhi-Hui Cheng, Jiujun Faculty of Engineering University of Toyama Toyama-shi Japan Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA College of Artificial Intelligence Nankai University Tianjin China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

Differential evolution (DE) is a widely recognized method to solve complex optimization problems as shown by many researchers. Yet, non-adaptive versions of DE suffer from insufficient exploration ability and uses no historical information for its performance enhancement. This work proposes Fractional Order Differential Evolution (FODE) to enhance DE performance from two aspects. Firstly, a bi-strategy co-deployment framework is proposed. The population-based and parameter-based strategies are combined to leverage their respective advantages. Secondly, the fractional order calculus is first applied to the differential vector to enhance DE’s exploration ability by using the historical information of populations, and ensures the diversity of population in an evolutionary process. We use the 2017 IEEE Congress on Evolutionary Computation (CEC) test functions, and CEC2011 real-world problems to evaluate FODE’s performance. Its sensitivity to parameter changes is discussed and an ablation study of multi-strategies is systematically performed. Furthermore, the variations of exploration and exploitation in FODE are visualized and analyzed. Experimental results show that FODE is superior to other state-of-the-art DE variants, the winners of CEC competitions, other fractional order calculus-based algorithms, and some powerful variants of classic algorithms. IEEE

关键词： Particle swarm optimization (PSO)

A new direction to promote the implementation of artificial intelligence in natural clinical settings

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Huang, Yunyou Zhang, Zhifei Wang, Nana Li, Nengquan Du, Mengjia Hao, Tianshu Zhan, Jianfeng State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Physiology and Pathophysiology Capital Medical University Beijing China Shenzhen University Shenzhen Guangdong China

Artificial intelligence (AI) researchers claim that they have made great 'achievements' in clinical realms. However, clinicians point out the so-called 'achievements' have no ability to implement into natural clinical settings. The root cause for this huge gap is that many essential features of natural clinical tasks are overlooked by AI system developers without medical background. In this paper, we propose that the clinical benchmark suite is a novel and promising direction to capture the essential features of the real-world clinical tasks, hence qualifies itself for guiding the development of AI systems, promoting the implementation of AI in real-world clinical practice. Copyright © 2019, The Authors. All rights reserved.

关键词：

AIBench training: Balanced industry-standard AI training benchmarking

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tang, Fei Gao, Wanling Zhan, Jianfeng Lan, Chuanxin Wen, Xu Wang, Lei Luo, Chunjie Cao, Zheng Xiong, Xingwang Jiang, Zihan Hao, Tianshu Fan, Fanda Zhang, Fan Huang, Yunyou Chen, Jianan Du, Mengjia Ren, Rui Zheng, Chen Zheng, Daoyi Tang, Haoning Zhan, Kunlin Wang, Biao Kong, Defei Yu, Minghe Tan, Chongkang Li, Huan Tian, Xinhui Li, Yatao Shao, Junchao Wang, Zhenyu Wang, Xiaoyu Dai, Jiahui Ye, Hainan State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Alibaba Baidu Tencent *** NetEase ByteDance Zhihu China Lenovo Paypal Moqi Microsoft Research Asia *** CloudTa Intellifusion

Earlier-stage evaluations of a new AI architecture/system need affordable AI benchmarks. Only using a few AI component benchmarks like MLPerf alone in the other stages may lead to misleading conclusions. Moreover, the learning dynamics are not well understood, and the benchmarks' shelf-life is short. This paper proposes a balanced benchmarking methodology. We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent. After performing an exhaustive survey on Internet service AI domains, we identify and implement nineteen representative AI tasks with state-of-the-art models. For repeatable performance ranking (RPR subset) and workload characterization (WC subset), we keep two subsets to a minimum for affordability. We contribute by far the most comprehensive AI training benchmark suite. The evaluations show: (1) AIBench Training (v1.1) outperforms MLPerf Training (v0.7) in terms of diversity and representativeness of model complexity, computational cost, convergent rate, computation, and memory access patterns, and hotspot functions;(2) Against the AIBench full benchmarks, its RPR subset shortens the benchmarking cost by 64%, while maintaining the primary workload characteristics;(3) The performance ranking shows the single-purpose AI accelerator like TPU with the optimized TensorFlow framework performs better than that of GPUs while losing the latter's general support for various AI models. The specification, source code, and performance numbers are available from the AIBench homepage https: //***/aibench-training/***. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

Diagnosis and Layout Aware (DLA) scan chain stitching

学校读者我要写书评

暂无评论

Diagnosis and Layout Aware (DLA) scan chain stitching

IEEE International Test Conference

作者： Jing Ye Yu Huang Yu Hu Wu-Tung Cheng Ruifeng Guo Liyang Lai Ting-Pu Tai Xiaowei Li Weipin Changchien Daw-Ming Lee Ji-Jan Chen Sandeep C. Eruvathi Kartik K. Kumara Charles Liu Sam Pan State Key Laboratory of Computer Architecture Institute of Computing Technology Beijing P. R. China Silicon Test Solutions Mentor Graphics Corp. Wilsonville OR USA Hsinchu Science Park Taiwan Semiconductor Manufacturing Company Hsinchu Taiwan

ISBN: (纸本)9781479908608

Without appropriate stitching of scan chains, even with good diagnosis algorithm and diagnostic pattern generation, it may still result in bad scan chain diagnostic resolution. To improve the diagnostic resolution, we propose a novel Diagnosis and Layout Aware (DLA) scan chain stitching method, which is pattern independent and supports embedded scan compaction. It is based on three ideas: (1) increasing the number of sensitive scan cells, which can capture useful diagnostic information; (2) properly distributing the sensitive scan cells along the scan chains to enhance the overall resolution; (3) stitching scan cells based on their placement at layout to preserve the chip performance. Experiments on ISCAS'89/ITC'99 benchmark circuits and a real industry circuit based on 20nm technology with silicon results show that, the proposed DLA scan chain stitching method effectively improves the resolution, with negligible impact on chip performance, embedded scan compaction, transition fault coverage, and test power dissipation. The silicon results even show 7X average resolution improvement comparing to without using the proposed method.

关键词： Circuit faults Layout Automatic test pattern generation Routing computer architecture Microprocessors Ant colony optimization

Effective low-power scan architecture-PowerCut

学校读者我要写书评

暂无评论

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2007年第3期44卷 473-478页

作者： Wang, Wei Han, Yinhe Hu, Yu Li, Xiaowei Zhang, Yousheng School of Computer and Information Hefei University of Technology Hefei 230009 China Advanced Test Technology Laboratory Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China

It is obvious that scan testing is the prevalent design for testability (DFT) in very large scale integrated circuits test. However, scan architecture in digital circuits causes much power consumption because when scan vectors are loaded into a scan chain, the effect of scan-ripple propagates to the combinational logic and redundant switching occurs in the combinational gates during the entire vectors shifting period. Hence, low-power design becomes a challenge for scan test. In this paper, a low-power scan architecture-PowerCut is proposed for minimizing power consumption during scan test, which is based on scan chain modification techniques. Blocking logic using transmission gates is inserted into the scan chain to reduce the dynamic power in shift cycle. At the same time, based on minimum leakage vector, a controlling unit is inserted. It makes the circuit slip into low leakage state during shift cycle. Thus, leakage power is also decreased. Experiments results indicate that this architecture can effectually reduce the power during scan test, and it has little improvement in area or delay overhead, compared with other low cost existing methods.

关键词： Integrated circuit testing

Generalized Visual Quality Assessment of GAN-Generated Face Images

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Yu Ni, Zhangkai Chen, Baoliang Wang, Shiqi Wang, Hanli Kwong, Sam The Department of Computer Science City University of Hong Kong 999077 Hong Kong The Department of Computer Science & Technology Tongji University Shanghai 200092 China The Department of Computer Science & Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai 200092 China The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China

Recent years have witnessed the dramatically increased interest in face generation with generative adversarial networks (GANs). A number of successful GAN algorithms have been developed to produce vivid face images towards different application scenarios. However, little work has been dedicated to automatic quality assessment of such GAN-generated face images (GFIs), even less have been devoted to generalized and robust quality assessment of GFIs generated with unseen GAN model. Herein, we make the first attempt to study the subjective and objective quality towards generalized quality assessment of GFIs. More specifically, we establish a large-scale database consisting of GFIs from four GAN algorithms, the pseudo labels from image quality assessment (IQA) measures, as well as the human opinion scores via subjective testing. Subsequently, we develop a quality assessment model that is able to deliver accurate quality predictions for GFIs from both available and unseen GAN algorithms based on meta-learning. In particular, to learn shared knowledge from GFIs pairs that are born of limited GAN algorithms, we develop the convolutional block attention (CBA) and facial attributes-based analysis (ABA) modules, ensuring that the learned knowledge tends to be consistent with human visual perception. Extensive experiments exhibit that the proposed model achieves better performance compared with the state-of-the-art IQA models, and is capable of retaining the effectiveness when evaluating GFIs from the unseen GAN algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

General capacity scaling of wireless networks

学校读者我要写书评

暂无评论

General capacity scaling of wireless networks

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Cheng Wang Changjun Jiang Xiang-Yang Li Shaojie Tang Panlong Yang Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Department of Computer Science University of Tongji Shanghai China Department of Computer Science Illinois Institute of Technology Chicago IL USA TNLIST School of Software Tsinghua University China People''s Liberation Army University of Science and Technology China

We study the general scaling laws of the capacity for random wireless networks under the generalized physical model. The generality of this work is embodied in three dimensions denoted by (λ ∈ [1, n], n d ∈ [1, n], n s ∈ (1, n]). It means that: (1) We study the random network of a general node density λ ∈ [1, n], rather than only study either random dense network (RDN, λ = n) or random extended network (REN, λ = 1) as in the literature. (2) We focus on the multicast capacity to unify unicast and broadcast capacities by setting the number of destinations for each session as a general value n d ∈ [1, n]. (3)We allow the number of sessions changing in the range n s ∈ (1, n], rather than assume that n s = Θ(n) as in the *** derive the general lower bounds on the capacity for the arbitrary case of (λ, n d , n s ). Particularly, we show that for the special cases (λ = 1, n d ∈ [1, n], n s = n) and (λ = n, n d ∈ [1, n], n s = n), our schemes achieve the highest multicast throughputs proposed in the existing works.

关键词： Roads Routing Throughput Lattices Schedules Mathematical model

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Ge...

International Conference on Parallel and Distributed systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：