检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ziqian Shao Tao Wang Kaihao Zhang Danhuai Zhao Tong Lu State Key Lab for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China China Mobile Zijin Innovation Insititute Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Low-light image enhancement problem has been widely studied. However, most existing methods do not perform well on low-light face images due to no specific facial characteristic considerations. We first create large-scale low-light face datasets with synthesized and real-world images to address the absence of suitable datasets. Our experiments show that existing LLIE and face restoration methods are limited in enhancing low-light face images. To overcome these challenges, we propose a novel framework, the Low-Light Face Adaptor (LLFA), featuring an auxiliary encoder and an adaptor module. The encoder captures global illumination information, while the adaptor module adaptively fuses this information with high-quality priors. We also introduce a joint learning strategy that optimizes the model by simultaneously learning face priors and the enhancement process. Comprehensive experiments demonstrate that LLFA significantly outperforms state-of-the-art methods.

关键词： Training Adaptation models Fuses Lighting Speech enhancement Signal processing Image restoration Faces Image enhancement Facial features

来源：评论

学校读者我要写书评

暂无评论

ATOM: Automated Black-Box Testing of Multi-label Image Classification Systems 23

ATOM: Automated Black-Box Testing of Multi-Label Image Class...

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated software Engineering

作者： Shengyou Hu Huayao Wu Peng Wang Jing Chang Yongjun Tu Xiu Jiang Xintao Niu Changhai Nie State Key Laboratory for Novel Software Technology and Department of Computer Science and Technology Nanjing University China Guangdong OPPO Mobile Telecommunications Corp. Ltd. China

ISBN: (纸本)9798350329964

Multi-label Image Classification Systems (MICSs) developed based on Deep Neural Networks (DNNs) are extensively used in people's daily life. Currently, although there are a variety of approaches to test DNN-based systems, they typically rely on the internals of DNNs to design test cases, and do not take the core specification of MICS (i.e., correctly recognizing multiple objects in a given image) into account. In this paper, we propose ATOM, an automated and systematic black-box testing framework for testing MICS. Specifically, ATOM exploits the label combination as the testing adequacy criteria, hoping to systematically examine the impact of correlations between a fixed number of labels on the classification ability of MICS. Then, ATOM leverages image search engine and natural language processing to find test images that are not only common to the real-world, but also relevant to target label combinations. Finally, ATOM combines metamorphic testing and label information to realize test oracle identification, based on which the ability of MICS in classifying different label combinations is evaluated. To evaluate the effectiveness of ATOM, we have performed experiments on two popular datasets of MICS, VOC and COCO (each with five state-of-the-art DNN models), and one real-world photo tagging application from our industrial partner. The experimental results reveal that the performance of current DNN-based MICSs remains less satisfactory even in recognizing correlations between only two labels, as ATOM triggers a total number of 6,049 such label combination related errors for all MICSs studied. In particular, ATOM reports 587 error-revealing images for the industrial MICS, in which 92% of them are confirmed by the developers.

关键词： multi-label image classification testing

来源：评论

学校读者我要写书评

暂无评论

Stochastic approximation approaches to group distributionally robust optimization 23

Stochastic approximation approaches to group distributionall...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Lijun Zhang Peng Zhao Zhen-Hua Zhuang Tianbao Yang Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University Nanjing China and Peng Cheng Laboratory Shenzhen China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Engineering Texas A & M University College Station

This paper investigates group distributionally robust optimization (GDRO), with the purpose to learn a model that performs well over m different distributions. First, we formulate GDRO as a stochastic convex-concave saddle-point problem, and demonstrate that stochastic mirror descent (SMD), using m samples in each iteration, achieves an O(m(log m)/ε2) sample complexity for finding an ε-optimal solution, which matches the Ω(m/ε2) lower bound up to a logarithmic factor. Then, we make use of techniques from online learning to reduce the number of samples required in each round from m to 1, keeping the same sample complexity. Specifically, we cast GDRO as a two-players game where one player simply performs SMD and the other executes an online algorithm for non-oblivious multi-armed bandits. Next, we consider a more practical scenario where the number of samples that can be drawn from each distribution is different, and propose a novel formulation of weighted GDRO, which allows us to derive distribution-dependent convergence rates. Denote by ni the sample budget for the i-th distribution, and assume n1 ≥ n2 ≥ ··· ≥ nm. In the first approach, we incorporate non-uniform sampling into SMD such that the sample budget is satisfied in expectation, and prove that the excess risk of the i-th distribution decreases at an $O(\sqrt{n_1 \log m}/n_i)$ rate. In the second approach, we use mini-batches to meet the budget exactly and also reduce the variance in stochastic gradients, and then leverage stochastic mirror-prox algorithm, which can exploit small variances, to optimize a carefully designed weighted GDRO problem. Under appropriate conditions, it attains an O((log m) / √ni) convergence rate, which almost matches the optimal O(√1/ni) rate of only learning from the i-th distribution with ni samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nerftap: Enhancing Transferability of Adversarial Patches on Face Recognition Using Neural Radiance Fields

SSRN

引用

SSRN 2024年

作者： Liu, Xiaoliang Shen, Furao Han, Feng Zhao, Jian Nie, Changhai National Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns. Existing research primarily focuses on transferability to different FR models, overlooking the direct transferability to victim's face images, which is a practical threat in real-world scenarios. In this study, we propose a novel adversarial attack method that considers both the transferability to the FR model and the victim's face image, called NeRFTAP. Leveraging Neural Radiance Fields (NeRF)-based 3D Generative Adversarial Network (GAN), we generate new view face images for the source and target subjects to enhance transferability of adversarial patches. We introduce a style consistency loss to ensure the visual similarity between the adversarial UV map and the target UV map under a 0-1 mask, enhancing the effectiveness and naturalness of the generated adversarial face images. Extensive experiments and evaluations on various FR models demonstrate the superiority of our approach over existing attack techniques. Our work provides valuable insights for enhancing the robustness of FR systems in practical adversarial settings. © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Estimation of the User Contribution Rate by Leveraging Time Sequence in Pairwise Matching function-point between Users Feedback and App Updating Log

arXiv

引用

arXiv 2023年

作者： Duan, Shiqi Liu, Jianxun Xiao, Yong Zhang, Xiangping School of Computer Science and Engineering Hunan University of Science and Technology Hunan China Hunan Key Lab for Services Computing and Novel Software Technology Hunan China

Mobile applications have become an inseparable part of people’s daily life. Nonetheless, the market competition is extremely fierce, and apps lacking recognition among most users are susceptible to market elimination. To this end, developers must swiftly and accurately apprehend the requirements of the wider user base to effectively strategize and promote their apps’ orderly and healthy evolution. The rate at which general user requirements are adopted by developers, or user contribution, is a very valuable metric that can be an important tool for app developers or software engineering researchers to measure or gain insight into the evolution of app requirements and predict the evolution of app software. Regrettably, the landscape lacks refined quantitative analysis approaches and tools for this pivotal indicator. To address this problem, this paper exploratively proposes a quantitative analysis approach based on the temporal correlation perception that exists in the app update log and user reviews, which provides a feasible solution for quantitatively obtaining the user contribution. The main idea of this scheme is to consider valid user reviews as user requirements and app update logs as developer responses, and to mine and analyze the pairwise and chronological relationships existing between the two by text computing, thus constructing a feasible approach for quantitatively calculating user contribution. To demonstrate the feasibility of the approach, this paper collects data from four Chinese apps in the App Store in mainland China and one English app in the U.S. region, including 2,178 update logs and 4,236,417 user reviews, and from the results of the experiment, it was found that 16.6%-43.2% of the feature of these apps would be related to the drive from the online popular user requirements. Copyright © 2023, The Authors. All rights reserved.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting

arXiv

引用

arXiv 2024年

作者： Li, Feifei Guo, Suhan Han, Feng Zhao, Jian Shen, Furao National Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Accurate forecasting of long-term time series has important applications for decision making and planning. However, it remains challenging to capture the long-term dependencies in time series data. To better extract long-term dependencies, We propose Multi-Scale Dilated Convolution Network (MSDCN), a method that utilizes a shallow dilated convolution architecture to capture the period and trend characteristics of long time series. We design different convolution blocks with exponentially growing dilations and varying kernel sizes to sample time series data at different scales. Furthermore, we utilize traditional autoregressive model to capture the linear relationships within the data. To validate the effectiveness of the proposed approach, we conduct experiments on eight challenging long-term time series forecasting benchmark datasets. The experimental results show that our approach outperforms the prior state-of-the-art approaches and shows significant inference speed improvements compared to several strong baseline methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Quantum Annealing for Quadratic Unconstrained Binary Optimization (QUBO) Problems

arXiv

引用

arXiv 2024年

作者： Xie, Moyang Zhang, Yuan Zhong, Sheng Li, Qun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science William & Mary WilliamsburgVA United States

Quantum annealers offer a promising approach to solve Quadratic Unconstrained Binary Optimization (QUBO) problems, which have a wide range of applications. However, when a user submits its QUBO problem to a third-party quantum annealer, the problem itself may disclose the user's private information to the quantum annealing service provider. To mitigate this risk, we introduce a privacy-preserving QUBO framework and propose a novel solution method. Our approach employs a combination of digit-wise splitting and matrix permutation to obfuscate the QUBO problem's model matrix Q, effectively concealing the matrix elements. In addition, based on the solution to the obfuscated version of the QUBO problem, we can reconstruct the solution to the original problem with high accuracy. Theoretical analysis and empirical tests confirm the efficacy and efficiency of our proposed technique, demonstrating its potential for preserving user privacy in quantum annealing services. © 2024, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network

AutoAC: Towards Automated Attribute Completion for Heterogen...

引用

International Conference on Data Engineering

作者： Guanghui Zhu Zhennan Zhu Wenjie Wang Zhuoer Xu Chunfeng Yuan Yihua Huang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural networks (GNNs) have received more and more attention. However, the existing work mainly focuses on the design of novel GNN models, while ignoring another important issue that also has a large impact on the model performance, namely the missing attributes of some node types. The handcrafted attribute completion requires huge expert experience and domain knowledge. Also, considering the differences in semantic characteristics between nodes, the attribute completion should be fine-grained, i.e., the attribute completion operation should be node-specific. Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes. To address the above challenges, we propose a differentiable attribute completion framework called AutoAC for automated completion operation search in heterogeneous GNNs. We first propose an expressive completion operation search space, including topology-dependent and topology-independent completion operations. Then, we propose a continuous relaxation schema and further propose a differentiable completion algorithm where the completion operation search is formulated as a bi-level joint optimization problem. To improve the search efficiency, we leverage two optimization techniques: discrete constraints and auxiliary unsupervised graph node clustering. Extensive experimental results on real-world datasets reveal that AutoAC outperforms the SOTA handcrafted heterogeneous GNNs and the existing attribute completion method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical spatiotemporal vortices

引用

eLight 2023年第1期3卷 156-168页

作者： Chenhao Wan Andy Chong Qiwen Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China School of Optical and Electronic Information and Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074HubeiChina Department of Physics Pusan National UniversityGeumjeong-GuBusan 46241South Korea Zhangjiang Laboratory 100 Haike RoadShanghai 201204China Shanghai Key Lab of Modern Optical System University of Shanghai for Science and TechnologyShanghai 200093China

Spatiotemporal vortices of light,featuring transverse orbital angular momentum(OAM)and energy circulation in the spatiotemporal domain,have received increasing attention *** experimental realization of the controllable generation of spatiotemporal vortices triggers a series of research in this *** review article covers the latest developments of spatiotemporal vortices of light ranging from theoretical physics,experimental generation schemes,and characterization methods,to applications and future *** new degree of freedom in photonic OAM endowed by spatiotemporal vortices paves the way to the discovery of novel physical mechanisms and photonic applications in light science.

关键词： Spatiotemporal optical vortex Orbital angular momentum Spin-orbit interaction Linear momentum density Toroidal vortex Topological charge

来源：评论

学校读者我要写书评

暂无评论

STSD: Modeling Spatial Temporal Staticity and Dynamicity in Traffic Forecasting

STSD: Modeling Spatial Temporal Staticity and Dynamicity in ...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Guanghui Zhu Haojun Hou Peiliang Wang Chunfeng Yuan Yihua Huang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

As one of the typical tasks of spatial temporal forecasting, traffic prediction has attracted extensive research attention in recent studies. Recent works usually combine time series modeling methods and graph neural networks to capture the temporal dynamic trends and spatial static dependencies together. However, we find that the temporal static characteristic and spatial dynamic correlations do also exist in the traffic flow, which are neglected or partially considered in previous methods. To capture such characteristics, we propose a novel method for traffic prediction, which models the Spatial Temporal Staticity and Dynamicity (STSD) together. Specifically, besides the traditional spatial and temporal encoder, we propose a pre-training module based on self-supervised contrastive learning to learn the location representation and thus capture the temporal static characteristic. Then, we propose a flow-aware dynamic graph learning module to capture the spatial dynamic correlations. Besides, to correct the original graph built from node distance, a feature reconstruction-based static graph learning module is introduced. The original, static, and dynamic graph are combined together in STSD to model the spatial staticity and dynamicity. Extensive experimental results on real-world datasets reveal that STSD can outperform existing traffic forecasting methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：