检索结果-内蒙古大学图书馆

Towards Task-Free Privacy-Preserving Data Collection

China Communications 2022年第7期19卷 310-323页

作者： Zhibo Wang Wei Yuan Xiaoyi Pang Jingxin Li Huajie Shao School of Cyber Science and Engineering Wuhan University430072 China School of Cyber Science and Technology Zhejiang University310027 China State Key Laboratory of Integrated Services Networks Xidian University710071 China Department of Computer Science College of William and MaryWilliamsburgVA23186 USA

With the rapid developments of Internet of Things(IoT)and proliferation of embedded devices,large volume of personal data are collected,which however,might carry massive private information about attributes that users do not want to *** privacy-preserving methods have been proposed to prevent privacy leakage by perturbing raw data or extracting task-oriented features at local ***,they would suffer from significant privacy leakage and accuracy drop when applied to other tasks as they are designed and optimized for predefined *** this paper,we propose a novel task-free privacy-preserving data collection method via adversarial representation learning,called TF-ARL,to protect private attributes specified by users while maintaining data utility for unknown downstream *** this end,we first propose a privacy adversarial learning mechanism(PAL)to protect private attributes by optimizing the feature extractor to maximize the adversary’s prediction uncertainty on private attributes,and then design a conditional decoding mechanism(ConDec)to maintain data utility for downstream tasks by minimizing the conditional reconstruction error from the sanitized *** the joint learning of PAL and ConDec,we can learn a privacy-aware feature extractor where the sanitized features maintain the discriminative information except *** experimental results on real-world datasets demonstrate the effectiveness of TF-ARL.

关键词： IoT privacy protection data collection adversarial learning deep learning

来源：评论

学校读者我要写书评

暂无评论

StructSR: Refuse Spurious Details in Real-World Image Super-Resolution

arXiv

引用

arXiv 2025年

作者： Li, Yachao Liang, Dong Ding, Tianyu Huang, Sheng-Jun College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing211106 China Microsoft Washington United States

Diffusion-based models have shown great promise in real-world image super-resolution (Real-ISR), but often generate content with structural errors and spurious texture details due to the empirical priors and illusions of these models. To address this issue, we introduce StructSR, a simple, effective, and plug-and-play method that enhances structural fidelity and suppresses spurious details for diffusion-based Real-ISR. StructSR operates without the need for additional fine-tuning, external model priors, or high-level semantic knowledge. At its core is the Structure-Aware Screening (SAS) mechanism, which identifies the image with the highest structural similarity to the low-resolution (LR) input in the early inference stage, allowing us to leverage it as a historical structure knowledge to suppress the generation of spurious details. By intervening in the diffusion inference process, StructSR seamlessly integrates with existing diffusion-based Real-ISR models. Our experimental results demonstrate that StructSR significantly improves the fidelity of structure and texture, improving the PSNR and SSIM metrics by an average of 5.27% and 9.36% on a synthetic dataset (DIV2KVal) and 4.13% and 8.64% on two real-world datasets (RealSR and DRealSR) when integrated with four state-of-the-art diffusion-based Real-ISR methods. Code - https://***/LYCEXE/StructSR. Copyright © 2025, The Authors. All rights reserved.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

Fast target-aware learning for few-shot video object segmentation

引用

science China(Information sciences) 2022年第8期65卷 71-86页

作者： Yadang CHEN Chuanyan HAO Zhi-Xin YANG Enhua WU Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and Technology School of Education Science and Technology Nanjing University of Posts and Telecommunications State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of Macau State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of Sciences Faculty of Science and Technology University of Macau

Few-shot video object segmentation(FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video *** proposed method is trained only on an individual public video object segmentation(VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouT ubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile,a high inference speed of approximately 0.13 s per frame is maintained.

关键词： video object segmentation few-shot target-aware meta knowledge bilevel-optimization

来源：评论

学校读者我要写书评

暂无评论

A Formal Specification Approach to Specify Pet's House System Using Z - Notations

A Formal Specification Approach to Specify Pet's House Syste...

引用

International Conference on Advanced Infocomm technology (ICAIT)

作者： Nibtal Khalid Irfan Ahmed Jabar Mahmood Qasim Ali Saman Abid Khadija Batool Department of Computer Science University of Sialkot Sialkot Pakistan State Key Laboratory of Blockchain School of Cyber Science and Technology College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350391497

ISBN: (纸本)9798350391503

The formal method (FM) is an innovative method that employs mathematical notations to describe explicit and precise requirements. This makes it possible to find errors and conflicts early in the software development process. To improve quality, the Z concept can assist with system specifications, design, and testing. A formal Specifications of a pet system is presented in this paper using the Z specification language. The complicated pet system is in charge of maintaining information about pets, owners, and numerous components of their care. We demonstrate how the requirements of the pet system, including its functionality, data structures, and behavior, can be specified using Z. In this specification, we aim to highlight the benefits of using formal methods to ensure the accuracy and reliability of complex systems and to show how valuable they are in system design and development. Formal approaches are advantageous not just for mission-critical systems, but also in commercial and business-oriented applications, since they could significantly decrease development time, verification, and maintenance costs. These results will serve as motivation for formal approaches.

关键词： Frequency modulation Costs System performance computer bugs software Maintenance Specification languages Formal specifications Testing software development management

来源：评论

学校读者我要写书评

暂无评论

Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation

Exploring Regional Clues in CLIP for Zero-Shot Semantic Segm...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yi Zhang Meng-Hao Guo Miao Wang Shi-Min Hu State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Department of Computer Science and Technology BNRist Tsinghua University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

CLIP has demonstrated marked progress in visual recognition due to its powerful pre-training on large-scale image-text pairs. However, it still remains a critical challenge: how to transfer image-level knowledge into pixel-level understanding tasks such as semantic segmentation. In this paper, to solve the mentioned challenge, we analyze the gap between the capability of the CLIP model and the requirement of the zero-shot semantic segmentation task. Based on our analysis and observations, we propose a novel method for zero-shot semantic segmentation, dubbed CLIP-RC (CLIP with Regional Clues), bringing two main insights. On the one hand, a region-level bridge is necessary to provide fine-grained semantics. On the other hand, over-fitting should be mitigated during the training stage. Benefiting from the above discoveries, CLIP-RC achieves state-of-the-art performance on various zero-shot semantic segmentation benchmarks, including PASCAL VOC, PASCAL Context, and COCO-Stuff 164K. Code will be available at https://***/Jittor/JSeg.

关键词： Training Bridges Visualization computer vision Image recognition Codes Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Li, Shumeng Qi, Lei Yu, Qian Huo, Jing Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China Southeast University China School of Data and Computer Science Shandong Women’s University China

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR). The current finetuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our stitching strategy mitigates the mismatch between natural and 3D medical images. The stitched images are then used for fine-tuning SAM, providing robust initialization of pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. We also develop an extended framework SFR+ with selective fine-tuning and re-training through confidence estimation. Extensive experiments validate that our SFR and SFR+ achieve significant improvements in both moderate annotation and scarce annotation across five datasets. In particular, SFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset. The code is available at https://***/ShumengLI/SFR. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

StructSR: Refuse Spurious Details in Real-World Image Super-Resolution 39

StructSR: Refuse Spurious Details in Real-World Image Super-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

Diffusion-based models have shown great promise in real-world image super-resolution (Real-ISR), but often generate content with structural errors and spurious texture details due to the empirical priors and illusions of these models. To address this issue, we introduce StructSR, a simple, effective, and plug-and-play method that enhances structural fidelity and suppresses spurious details for diffusion-based Real-ISR. StructSR operates without the need for additional fine-tuning, external model priors, or high-level semantic knowledge. At its core is the Structure-Aware Screening (SAS) mechanism, which identifies the image with the highest structural similarity to the low-resolution (LR) input in the early inference stage, allowing us to leverage it as a historical structure knowledge to suppress the generation of spurious details. By intervening in the diffusion inference process, StructSR seamlessly integrates with existing diffusion-based Real-ISR models. Our experimental results demonstrate that StructSR significantly improves the fidelity of structure and texture, improving the PSNR and SSIM metrics by an average of 5.27% and 9.36% on a synthetic dataset (DIV2KVal) and 4.13% and 8.64% on two real-world datasets (RealSR and DRealSR) when integrated with four state-of-the-art diffusion-based Real-ISR methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DrugProtKGE: Weakly Supervised Knowledge Graph Embedding for Highly-Effective Drug-Protein Interaction Representation

DrugProtKGE: Weakly Supervised Knowledge Graph Embedding for...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Qiu, Yanlong Wang, Siqi Yang, Xi Qiu, Xinyuan Wu, Chengkun Cui, Yingbo Yang, Canqun National University of Defense Technology Institute for Quantum Information State Key Laboratory of High-Performance Computing College of Computer Science Hunan Changsha410073 China National Supercomputer Center in Tianjin Tianjin300457 China National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing College of Computer Science Hunan Changsha410073 China National University of Defense Technology Department of Biology and Chemistry College of Science Hunan Changsha410073 China

ISBN: (纸本)9798350337488

With the exponential growth of biomedical knowledge in unstructured text repositories such as PubMed, it is imminent to establish a knowledge graph-style, efficient searchable and targeted database that can support the need of information retrieval from researchers and clinicians. To mine knowledge from graph databases, most previous methods view a triple in a graph (see Fig. 1) as the basic processing unit and embed the triplet element (i.e. drugs/chemicals, proteins/genes and their interaction) as separated embedding matrices, which cannot capture the semantic correlation among triple elements. To remedy the loss of semantic correlation caused by disjoint embeddings, we propose a novel approach to learn triple embeddings by combining entities and interactions into a unified representation. Furthermore, traditional methods usually learn triple embeddings from scratch, which cannot take advantage of the rich domain knowledge embedded in pre-trained models, and is also another significant reason for the fact that they cannot distinguish the differences implied by the same entity in the multi-interaction triples. In this paper, we propose a novel fine-tuning based approach to learn better triple embeddings by creating weakly supervised signals from pre-trained knowledge graph embeddings. The method automatically samples triples from knowledge graphs and estimates their pairwise similarity from pre-trained embedding models. The triples are then fed pairwise into a Siamese-like neural architecture, where the triple representation is fine-tuned in the manner bootstrapped by triple similarity scores. Finally, we demonstrate that triple embeddings learned with our method can be readily applied to several downstream applications (e.g. triple classification and triple clustering). We evaluated the proposed method on two open-source drug-protein knowledge graphs constructed from PubMed abstracts, as provided by BioCreative. Our method achieves consistent improvement in both t

关键词： Drug-Protein Interaction Knowledge Graph Embedding Triple Embedding Weakly Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoder

arXiv

引用

arXiv 2024年

作者： Han, Tingxu Huang, Shenghan Ding, Ziqi Sun, Weisong Feng, Yebo Fang, Chunrong Li, Jun Qian, Hanwei Wu, Cong Zhang, Quanjun Liu, Yang Chen, Zhenyu The State Key Laboratory for Novel Software Technology Nanjing University Jiangsu210093 China The School of Computer Science University of New South Wales NSW2052 Australia The School of Computer Science and Engineering Nanyang Technological University Nanyang639798 Singapore The Department of Computer Science The Director of the Network & Security Research Laboratory The University of Oregon United States

With the development of deep learning, self-supervised learning (SSL) has become particularly popular. SSL pre-trains an encoder (e.g., an image encoder) to learn generic features from a large amount of unlabeled data, releases it on a third-party platform, and allows any downstream task (e.g., an image classification task) to further fine-tune the encoder with task-specific data to derive the model for the task. However, despite the tremendous performance improvements it brings, SSL faces serious security risks. An adversary can poison pre-training datasets used to pre-train an encoder or publish a poisoned encoder directly to third-party platforms, which will also poison the model for any downstream task that uses these encoders. In this paper, we study a defense against poisoned encoders in SSL called distillation, which is a defense used in supervised learning originally. Distillation aims to distill knowledge from a given model (a.k.a the teacher net) and transfer it to another (a.k.a the student net). Now, we use it to distill benign knowledge from poisoned pre-trained encoders and transfer it to a new encoder, resulting in a clean pre-trained encoder. In particular, we conduct an empirical study on the effectiveness and performance of distillation against poisoned encoders. Using two state-of-the-art backdoor attacks against pre-trained image encoders and four commonly used image classification datasets, our experimental results show that distillation can reduce attack success rate from 80.87% to 27.51% while suffering a 6.35% loss in accuracy. Moreover, we investigate the impact of three core components of distillation on performance: Teacher net, student net, and distillation loss. By comparing 4 different teacher nets, 3 student nets, and 6 distillation losses, we find that fine-tuned teacher nets, warm-up-training-based student nets, and attention-based distillation loss perform best, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis for Limited Similar Batch Process using Two-dimensional Adversarial Domain Adaptation-based Graph Convolutional Network 43

Fault Diagnosis for Limited Similar Batch Process using Two-...

引用

43rd Chinese Control Conference, CCC 2024

作者： Gao, Xingke Zhang, Zheng Zhu, Jinlin Jiangnan University School of Artificial Intelligence and Computer Science Wuxi214122 China Hong Kong University of Science and Technology Department of Chemical and Biological Engineering Clear Water Bay Kowloon999077 Hong Kong Jiangnan University State Key Laboratory of Food Science and Resources Wuxi214122 China Jiangnan University School of Food Science and Technology Wuxi214122 China

ISBN: (纸本)9789887581581

Batch process fault diagnosis is critical for ensuring the quality and safety of batch processes production. However, recognizing fault types in low-volume and similar batch processes poses a significant challenge. This paper proposes a novel domain-adaptive transfer learning model named two-dimensional adversarial domain adaptation-based graph convolutional network (2D-ADGCN) for limited similar batch process fault diagnosis. Firstly, the method creates enhanced samples by integrating statistical information within a two-dimensional sliding window, significantly expanding the scale of the analyzed data by sliding the window in both time and batch dimensions. Secondly, by constructing an adversarial domain adaptation graph convolutional network, the data from the source domain (original batches) and the target domain (similar batches) are mapped into a shared feature space, reducing the distribution discrepancy between the two domains. Then, leveraging the labeled samples from the source domain, the model learns discriminative representations for the samples and performs classification on the target domain samples, enabling fault diagnosis for similar batches. Finally, the effectiveness of 2D-ADGCN is validated through industrial case studies of two Lactobacillus plantarum fed-batch fermentation processes, demonstrating its significant potential for fault diagnosis in low-volume and similar batch processes. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Convolution

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：