检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Kaiyu Cao, Xiangyong Deng, Yupeng Song, Jiayi Liu, Junmin Meng, Deyu Wang, Zhi School of Software Engineering Xi’an Jiaotong University Xi’an710049 China School of Computer Science and Technology Ministry of Education Key Lab For Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an China Guangdong Guangzhou China

Change Detection (CD) aims to identify pixels with semantic changes between images. However, annotating massive numbers of pixel-level images is lab.r-intensive and costly, especially for multi-temporal images, which require pixel-wise comparisons by human experts. Considering the excellent performance of visual language models (VLMs) for zero-shot, open-vocabulary, etc. with prompt-based reasoning, it is promising to utilize VLMs to make better CD under limited lab.led data. In this paper, we propose a VLM guidance-based semisupervised CD method, namely SemiCD-VL. The insight of SemiCD-VL is to synthesize free change lab.ls using VLMs to provide additional supervision signals for unlab.led data. However, almost all current VLMs are designed for single-temporal images and cannot be directly applied to bi- or multi-temporal images. Motivated by this, we first propose a VLM-based mixed change event generation (CEG) strategy to yield pseudo lab.ls for unlab.led CD data. Since the additional supervised signals provided by these VLM-driven pseudo lab.ls may conflict with the original pseudo lab.ls from the consistency regularization paradigm (e.g. FixMatch), we propose the dual projection head for de-entangling different signal sources. Further, we explicitly decouple the bi-temporal images semantic representation through two auxiliary segmentation decoders, which are also guided by VLM. Finally, to make the model more adequately capture change representations, we introduce contrastive consistency regularization by constructing feature-level contrastive loss in auxiliary branches. Extensive experiments show the advantage of SemiCD-VL. For instance, SemiCD-VL improves the FixMatch baseline by +5.3 IoUc on WHU-CD and by +2.4 IoUc on LEVIR-CD with 5% lab.ls, and SemiCD-VL requires only 5% to 10% of the lab.ls to achieve performance similar to the supervised methods. In addition, our CEG strategy, in an un-supervised manner, can achieve performance far superior to state-of-t

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

arXiv

引用

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Secure linear aggregation using decentralized threshold additive homomorphic encryption for federated learning

arXiv

引用

arXiv 2021年

作者： Tian, Haibo Zhang, Fangguo Shao, Yunfeng Li, Bingshuai The GuangDong Province Key Laboratory of Information Security Technology School of Data and Computer Science Sun Yat-Sen University Guangdong Guangzhou510275 China Huawei Noah's Ark Lab.

Secure linear aggregation is to linearly aggregate private inputs of different users with privacy protection. The server in a federated learning (FL) environment can fulfill any linear computation on private inputs of users through the secure linear aggregation. At present, based on pseudo-random number generator and one-time padding technique, one can efficiently compute the sum of user inputs in FL, but linear calculations of user inputs are not well supported. Based on decentralized threshold additive homomorphic encryption (DTAHE) schemes, this paper provides a secure linear aggregation protocol, which allows the server to multiply the user inputs by any coefficients and to sum them together, so that the server can build a full connected layer or a convolution layer on top of user inputs. The protocol adopts the framework of Bonawitz et al. to provide fault tolerance for user dropping out, and exploits a blockchain smart contract to encourage the server honest. The paper gives a security model, security proofs and a concrete lattice based DTAHE scheme for the protocol. It evaluates the communication and computation costs of known DTAHE construction methods. The evaluation shows that an elliptic curve based DTAHE is friendly to users and the lattice based version leads to a light computation on the server. Copyright © 2021, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Hfcyclegan: High-Frequency information Guided Cycle-Consistent Adversarial Network for Fundus Image Enhancement

SSRN

引用

SSRN 2025年

作者： Liu, Shaopeng Wang, Kai Wu, Xiaohang Xu, Fabao Zhou, Ying Wang, Xinpeng Wang, Qinkang Cen, Haoran Guo, Jianhua Lu, Xu School of Computer Science Guangdong Polytechnic Normal University Guangzhou510665 China Zhongshan Ophthalmic Center State Key Laboratory of Ophthalmology Sun Yat-Sen University Guangdong Guangzhou China Qilu Hospital Shandong University Jinan China Shenzhen Institute of Information Technology Shenzhen China Guangdong Provincial Key Laboratory of Intellectual Property & Big Data Guangzhou510665 China Pazhou Lab Guangzhou510330 China

The development of fundus imaging techniques has greatly supported the diagnosis of ophthalmic *** advancements, poor imaging quality, such as artifacts or insufficient illumination, poses challenges for disease *** clinical, it is often difficult to obtain paired data for fundus image enhancement. For unpaired data, CycleGAN-based methods are commonly used to learn the style transfer from low-quality images to high-quality images for enhancement, improving the aforementioned transfer process through brightness loss or regularization ***, fundus images are quite complex, and high-quality images can also exhibit uneven *** methods are not efficient in modeling the characteristics of fundus *** wavelet analysis, we found that the texture information represented by vessels is expressed in the high-frequency components of the ***, we designed a high-frequency information guided cycle-consistent generative adversarial network for unpaired fundus image enhancement, termed *** introduces a novel high-frequency guided generator (HFGen) and a corresponding frequency-aware discriminator (FADis).Specifically, HG uses the proposed high-frequency feature extraction module (HFM) to extract high-frequency features and inject them into the decoding process, outside of the main branches of the *** concatenate the input image with the frequency components obtained from wavelet transformation and input them into *** embedded channel-wise attention blocks of discriminator enable HFCycleGAN to focus on the frequency information differences between low-quality and high-quality fundus *** experiments on two real-world datasets and one synthetic dataset verify that HFcycleGAN outperforms existing *** conclusion, the HFcycleGAN effectively enhances important structures such as vessels in fundus images, significantly impacting fundus image analysis. © 2025, The Author

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Rsh-Bu: Revocable Secret Handshakes with Backward Unlinkability from Vlr Group Signatures

SSRN

引用

SSRN 2023年

作者： Wen, Yamin Wan, Min Zhao, Junying Gong, Zheng Deng, Yuqiao School of Statistics and Mathematics Guangdong University of Finance and Economics Guangzhou510320 China Guangdong Provincial Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510006 China Big Data and Education Statistics Application Laboratory Guangdong University of Finance and Economics Guangzhou510320 China School of Information Guangdong University of Finance and Economics Guangzhou510320 China School of Computer Science South China Normal University Guangzhou510631 China

Secret handshake scheme is a bi-directional authentication method that enables two participants from the same organization to identify both sides in private. A new generic construction of secret handshakes is proposed in this paper, which is basically derived from verifier-local revocation group signature (VLR-GS). Accordingly, a secret handshake scheme instance is illustrated from a short VLR-GS with backward unlinkability. Our scheme implements an efficient revocation mechanism that also ensures traceability and unlinkability. In addition, the past behaviors of revoked users still keep confidential because of the mechanism of backward unlinkability. We also strengthen the communication protection between Group Authority (GA) and members, such that group members will not be forged by malicious GA. Compared with the previous secret handshake schemes, our scheme greatly reduces the communication and computation overhead, so it is especially suitable for mobile environments. Due to the difficulty of Decision Linear (DLIN) and q-Strong Diffie-Hellman (q-SDH) problems, our proposal can be proved to be secure under the random oracle model. © 2023, The Authors. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Reversible data Hiding Based on Partitioning the Prediction Values 18th

Reversible Data Hiding Based on Partitioning the Prediction ...

引用

18th International Workshop on Digital Forensics and Watermarking, IWDW 2019

作者： Wu, Haihang Huang, Fangjun Guangdong Provincial Key Laboratory of Information Security Technology School of Data and Computer Science Sun Yat-Sen University GuangzhouGD510006 China

ISBN: (纸本)9783030435745

In this paper, we present a new reversible data hiding (RDH) method. Instead of directly dividing the neighboring pixels into blocks, we sort the pixels according to their prediction values first, and then the sorted sequence is partitioned into non-overlapping blocks. That is, different from that in pixel value ordering (PVO) series only the neighboring pixels can be divided into the same block, in our new scheme the pixels far apart from each other in space may be divided into the same block in case they have the similar pixel values. Thus much redundancy in image can be exploited and a sharper prediction error histogram is easy to be obtained for data embedding. To achieve better performance, a new adaptive embedding strategy is also proposed. The experimental results show that our new method is superior to the traditional PVO based methods. © 2020, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

ICSGD-Momentum: SGD Momentum Based on Inter-gradient Collision

ICSGD-Momentum: SGD Momentum Based on Inter-gradient Collisi...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weidong Zou Weipeng Cao Yuanqing Xia Bineng Zhong Dachuan Li School of Automation Beijing Institute of Technology Beijing China Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Deep neural networks (DNNs) are widely used in fields like computer vision and natural language processing. A key component of DNN training is the optimizer. SGD-Momentum is popular in many DNN methodologies, such as ResNet and DenseNet, due to its simplicity and effectiveness. However, its slow convergence rate limits its use. To overcome this, we introduce inter-gradient collision into SGD-Momentum, inspired by the elastic collision model in physics. This new method, called ICSGD-Momentum, aims to improve convergence. We provide theoretical proof of convergence and establish a regret bound for ICSGD-Momentum. Experiments on benchmarks including function optimization, CIFAR-100, ImageNet, Penn Treebank, COCO, and YCB-Video show that ICSGD-Momentum accelerates training and enhances the generalization performance of DNNs compared to optimizers like SGD-Momentum, Adam, Radam, Adabound, and AdaBelief.

关键词： Training computer vision Artificial neural networks Benchmark testing Natural language processing Informatics Physics Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

A rejection sampling algorithm for off-centered discrete Gaussian distributions over the integers

引用

science China(information sciences) 2019年第3期62卷 196-198页

作者： Yusong DU Baodian WEI Huang ZHANG School of Data and Computer Science Sun Yat-sen University Guangdong Key Laboratory of Information Security Technology Chongqing Key Lab of Computer Network and Communication Technology

Dear editor,Discrete Gaussian sampling, that is, sampling from a discrete Gaussian distribution DΛ,σ,cwith parameter σ> 0 and center c∈R~n over an ndimensional lattice Λ, has been considered by the cryptography research community as one of the fundamental building blocks of lattice-based cryptography [1, 2]. The simplest lattice is the one-

关键词： A rejection sampling algorithm for off-centered discrete Gaussian distributions over the integers

来源：评论

学校读者我要写书评

暂无评论

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications

arXiv

引用

arXiv 2023年

作者： Lin, Jiatai Han, Guoqiang Xu, Xuemiao Liang, Changhong Wong, Tien-Tsin Chen, C.L. Philip Liu, Zaiyi Han, Chu The School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Southern Medical University Guangzhou510080 China School of Computer Science and Engineering South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Class activation mapping (CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation (WSSS) and object localization (WSOL). It is the weighted aggregation of the feature maps by activating the high class-relevance ones. Current CAM methods achieve it relying on the training outcomes, such as predicted scores (forward information), gradients (backward information), etc. However, when with small-scale data, unstable training may lead to less effective model outcomes and generate unreliable weights, finally resulting in incorrect activation and noisy CAM seeds. In this paper, we propose an outcome-agnostic CAM approach, called BroadCAM, for small-scale weakly supervised applications. Since broad learning system (BLS) is independent to the model learning, BroadCAM can avoid the weights being affected by the unreliable model outcomes when with small-scale data. By evaluating BroadCAM on VOC2012 (natural images) and BCSS-WSSS (medical images) for WSSS and OpenImages30k for WSOL, BroadCAM demonstrates superior performance than existing CAM methods with small-scale data (less than 5%) in different CNN architectures. It also achieves SOTA performance with large-scale training data. Extensive qualitative comparisons are conducted to demonstrate how BroadCAM activates the high class-relevance feature maps and generates reliable CAMs when with small-scale training data. © 2023, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal

arXiv

引用

arXiv 2023年

作者： Leng, Yicheng Fang, Chaowei Li, Gen Fang, Yixiang Li, Guanbin School of Artificial Intelligence Xidian University Xi’an China School of Data Science The Chinese University of Hong Kong Shenzhen China Afirstsoft Shenzhen China School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China GuangDong Province Key Laboratory of Information Security Technology China

Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference of watermarks and restore the background content. However, existing methods often implement watermark component removal and background restoration tasks within a singular branch, leading to residual watermarks in the predictions and ignoring cases where watermarks heavily obscure the background. To address these limitations, this study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks and peripheral contextual information from unaffected regions. Moreover, a Global and Local Context Interaction module is built upon multi-layer perceptrons and bidirectional feature transformation for comprehensive representation modeling in the background restoration phase. The efficacy of our approach is empirically validated across two large-scale datasets, and our findings reveal a marked enhancement over existing watermark removal techniques. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

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：