检索结果-内蒙古大学图书馆

DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Du, Bo Tao, Dacheng Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China The University of Sydney Australia Jd Explore Academy China National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling. In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation. To address these challenges, this paper proposes a concise Dynamic Point Text DEtection TRansformer network, termed DPText-DETR. In detail, DPText-DETR directly leverages explicit point coordinates to generate position queries and dynamically updates them in a progressive way. Moreover, to improve the spatial inductive bias of non-local self-attention in Transformer, we present an Enhanced Factorized Self-Attention module which provides point queries within each instance with circular shape guidance. Furthermore, we design a simple yet effective positional label form to tackle the side effect of the previous form. To further evaluate the impact of different label forms on the detection robustness in real-world scenario, we establish an Inverse-Text test set containing 500 manually labeled images. Extensive experiments prove the high training efficiency, robustness, and state-of-the-art performance of our method on popular benchmarks. The code and the Inverse-Text test set are available at https://***/ymy-k/DPText-DETR. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

Quantum Differentially Private Sparse Regression Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Du, Yuxuan Hsieh, Min-Hsiu Liu, Tongliang You, Shan Tao, Dacheng School of Computer Science Faculty of Engineering The University of Sydney JD Explore Academy Beijing101111 China Hon Hai Quantum Computing Research Center Taipei114 Taiwan Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology Sydney Sydney2006 Australia SenseTime Beijing100080 China

The eligibility of various advanced quantum algorithms will be questioned if they can not guarantee privacy. To fill this knowledge gap, here we devise an efficient quantum differentially private (QDP) Lasso estimator to solve sparse regression tasks. Concretely, given N d-dimensional data points with N d, we first prove that the optimal classical and quantum non-private Lasso requires Ω(N+d) and Ω(√N+ √d) runtime, respectively. We next prove that the runtime cost of QDP Lasso is dimension independent, i.e., O(N5/2), which implies that the QDP Lasso can be faster than both the optimal classical and quantum non-private Lasso. Last, we exhibit that the QDP Lasso attains a near-optimal utility bound Õ(N−2/3) with privacy guarantees and discuss the chance to realize it on near-term quantum chips with advantages. © 2020, CC BY-NC-ND.

关键词： Machine learning

A hybrid floor identification algorithm based on Bayesian classification and special AP

学校读者我要写书评

暂无评论

A hybrid floor identification algorithm based on Bayesian cl...

International Conference on Information and Automation (ICIA)

作者： Fang Zhao Dan Luo Wu Yuan Haiyong Luo School of Software Engineering International School Beijing University of Posts and Telecommunications Beijing China NSFC Taiyuan-Zhongguancun Cooperation School of Computer Science Beijing Institute of Technology Beijing China Research Centre of Pervasive Computing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479940998

Accurately discriminating different floors is a very important task in indoor fingerprinting localization, which can be used to reduce space search domain and improve localization accuracy. There exist some research works for floor identification at present; however, the accuracy is not high. To achieve higher accuracy, this paper proposes a hybrid floor identification algorithm using Bayesian classification and special AP. By extracting the distribution feature of APs in different floors with training data, the proposed approach can determine floor efficiently with 100% accuracy.

关键词： Floors IEEE 802.11 Standards Bayes methods Accuracy Classification algorithms Training

Self-Evolution Learning for Discriminative Language Model Pretraining

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China University of Sydney Australia

Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence meaning, where some of them are more worthy to be predicted. Therefore, various masking strategies (e.g., entity-level masking) are proposed, but most of them require expensive prior knowledge and generally train from scratch without reusing existing model weights. In this paper, we present Self-Evolution learning (SE), a simple and effective token masking and learning method to fully and wisely exploit the knowledge from data. SE focuses on learning the informative yet under-explored tokens and adaptively regularizes the training by introducing a novel Token-specific Label Smoothing approach. Experiments on 10 tasks show that our SE brings consistent and significant improvements (+1.43∼2.12 average scores) upon different PLMs. In-depth analyses demonstrate that SE improves linguistic knowledge learning and generalization. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

A Principled Design of Image Representation: Towards Forensic Tasks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qi, Shuren Zhang, Yushu Wang, Chao Zhou, Jiantao Cao, Xiaochun The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China The Institute of Information Engineering Chinese Academy of Sciences Beijing China The Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China The State Key Laboratory of Internet of Things for Smart City China The Department of Computer and Information Science Faculty of Science and Technology University of Macau China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China

Image forensics is a rising topic as the trustworthy multimedia content is critical for modern society. Like other vision-related applications, forensic analysis relies heavily on the proper image representation. Despite the importance, current theoretical understanding for such representation remains limited, with varying degrees of neglect for its key role. For this gap, we attempt to investigate the forensic-oriented image representation as a distinct problem, from the perspectives of theory, implementation, and application. Our work starts from the abstraction of basic principles that the representation for forensics should satisfy, especially revealing the criticality of robustness, interpretability, and coverage. At the theoretical level, we propose a new representation framework for forensics, called dense invariant representation (DIR), which is characterized by stable description with mathematical guarantees. At the implementation level, the discrete calculation problems of DIR are discussed, and the corresponding accurate and fast solutions are designed with generic nature and constant complexity. We demonstrate the above arguments on the dense-domain pattern detection and matching experiments, providing comparison results with state-of-the-art descriptors. Also, at the application level, the proposed DIR is initially explored in passive and active forensics, namely copy-move forgery detection and perceptual hashing, exhibiting the benefits in fulfilling the requirements of such forensic tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image representation

Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xiaoqi Cheng, Yingjie Yang, Yaning Yu, Yue Li, Fei Peng, Shaoliang College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Institute of Open Source Software and Platform Peng Cheng Laboratory Shenzhen518000 China Computer Network Information Center Chinese Academy of Sciences Beijing100850 China The State Key Laboratory of Chemo/Biosensing and Chemometrics Hunan University Changsha410082 China

Self-supervised representation learning (SSL) on biomedical networks provides new opportunities for drug discovery. However, how to effectively combine multiple SSL models is still challenging and has been rarely explored. Therefore, we propose multitask joint strategies of self-supervised representation learning on biomedical networks for drug discovery, named MSSL2drug. We design six basic SSL tasks inspired by various modality features including structures, semantics, and attributes in heterogeneous biomedical networks. Importantly, fifteen combinations of multiple tasks are evaluated by a graph attention-based multi-task adversarial learning framework in two drug discovery scenarios. The results suggest two important findings. (1) Combinations of multimodal tasks achieve the best performance compared to other multi-task joint models. (2) The local-global combination models yield higher performance than random two-task combinations when there are the same size of modalities. Therefore, we conjecture that the multimodal and local-global combination strategies can be treated as the guideline of multi-task SSL for drug discovery. © 2022, CC BY-SA.

关键词： Semantics

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Tianfu Shen, Li Fan, Qilin Xu, Tong Liu, Tongliang Xiong, Hui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230027 China The School of Big Data and Software Engineering Chongqing University ChinaScience Chongqing401331 China JD Explore Academy The UBTECH Sydney Artificial Intelligence Centre The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney DarlingtonNSW2008 Australia Thrust of Artificial Intelligence Nansha Guangdong Guangzhou511400 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at https://***/GeminiLight/hrl-acra. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jiahe Zhang, Jiawei Bai, Xiao Zheng, Jin Ning, Xin Zhou, Jun Gu, Lin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University China Institute of Semiconductors Chinese Academy of Sciences China School of Information and Communication Technology Griffith University Australia RIKEN AIP Japan The University of Tokyo Japan

Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized framework based on 3D Gaussian radiance fields, offering real-time and high-quality few-shot novel view synthesis at low costs. Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease. In the Gaussian radiance fields, we find this degradation in scene geometry primarily lined to the positioning of Gaussian primitives and can be mitigated by depth constraint. Consequently, we propose a Hard and Soft Depth Regularization to restore accurate scene geometry under coarse monocular depth supervision while maintaining a fine-grained color appearance. To further refine detailed geometry reshaping, we introduce Global-Local Depth Normalization, enhancing the focus on small local depth changes. Extensive experiments on LLFF, DTU, and Blender datasets demonstrate that DNGaussian outperforms state-of-the-art methods, achieving comparable or better results with significantly reduced memory cost, a 25× reduction in training time, and over 3000× faster rendering speed. Code is available at: https://***/Fictionarry/DNGaussian. Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

High-Frequency Space Diffusion Model for Accelerated MRI

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Chentao Cui, Zhuo-Xu Wang, Yue Liu, Shaonan Chen, Taijin Zheng, Hairong Liang, Dong Zhu, Yanjie Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China The School of Artificial Intelligence The University of Chinese Academy of Sciences Beijing China Research Center for Medical AI Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen518000 China Pazhou Lab Guangzhou China The School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Diffusion models with continuous stochastic differential equations (SDEs) have shown superior performances in image generation. It can serve as a deep generative prior to solving the inverse problem in magnetic resonance (MR) reconstruction. However, low-frequency regions of k-space data are typically fully sampled in fast MR imaging, while existing diffusion models are performed throughout the entire image or k-space, inevitably introducing uncertainty in the reconstruction of low-frequency regions. Additionally, existing diffusion models often demand substantial iterations to converge, resulting in time-consuming reconstructions. To address these challenges, we propose a novel SDE tailored specifically for MR reconstruction with the diffusion process in high-frequency space (referred to as HFS-SDE). This approach ensures determinism in the fully sampled low-frequency regions and accelerates the sampling procedure of reverse diffusion. Experiments conducted on the publicly available fastMRI dataset demonstrate that the proposed HFS-SDE method outperforms traditional parallel imaging methods, supervised deep learning, and existing diffusion models in terms of reconstruction accuracy and stability. The fast convergence properties are also confirmed through theoretical and experimental validation. Our code and weights are available at https://***/Aboriginer/HFS-SDE. Copyright © 2022, The Authors. All rights reserved.

关键词： Magnetic resonance imaging