检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sun, Dongwei Bao, Yajie Liu, Junmin Cao, Xiangyong School of Computer Science and Technology the Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China Department of Information Science School of Mathematics and Statistics Xi’an Jiaotong University No.28 Xianning West Road Shaanxi Xi’an710049 China

Remote sensing image change captioning (RSICC) aims to automatically generate sentences that describe content differences in remote sensing bitemporal images. Recently, attention-based transformers have become a prevalent idea for capturing the features of global change. However, existing transformer-based RSICC methods face challenges, e.g., high parameters and high computational complexity caused by the self-attention operation in the transformer encoder component. To alleviate these issues, this paper proposes a Sparse Focus Transformer (SFT) for the RSICC task. Specifically, the SFT network consists of three main components, i.e. a high-level features extractor based on a convolutional neural network (CNN), a sparse focus attention mechanism-based transformer encoder network designed to locate and capture changing regions in dual-temporal images, and a description decoder that embeds images and words to generate sentences for captioning differences. The proposed SFT network can reduce the parameter number and computational complexity by incorporating a sparse attention mechanism within the transformer encoder network. Experimental results on various datasets demonstrate that even with a reduction of over 90% in parameters and computational complexity for the transformer encoder, our proposed network can still obtain competitive performance compared to other state-of-the-art RSICC methods. The code is available at Lite_Chag2cap. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

OAA: An Abstraction for Efficient Accelerator Adaptation in Deep Learning Frameworks

OAA: An Abstraction for Efficient Accelerator Adaptation in ...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Zhengxian Lu Chengkun Du Xueshuo Xie Qiankun Dong Cheng Gong Tao Li College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Huawei Technologies Zhejiang China Haihe Lab of ITAI Tianjin China College of Software Nankai University Tianjin China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Deep learning frameworks rely on specific runtime and computation libraries to rewrite the backend for the adaptation of specialized accelerators, which is inefficient and hard to guarantee performance. This paper solves the issue by proposing an Operator Adaptation Abstraction (OAA) that lies between the framework and the libraries. In addition, this paper optimizes training performance based on the hardware characteristics of the accelerator. We designed experiments based on Ascend 910 and OneFlow to verify the effectiveness of OAA. Our adaptation includes more than 50 Ascend operators, achieving up to 2.0x throughput compared to the official adaptation version of PyTorch. The experiments validate that the adaptation method proposed in this paper can effectively retain the advantages of both the framework and the accelerator.

关键词： Deep learning Training Runtime Neural networks Throughput Libraries Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

SAM-Event-Adapter: Adapting Segment Anything Model for Event-RGB Semantic Segmentation

SAM-Event-Adapter: Adapting Segment Anything Model for Event...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Bowen Yao Yongjian Deng Yuhan Liu Hao Chen Youfu Li Zhen Yang College of Computer Science Beijing University of Technology Beijing China Key Lab of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing China Department of Mechanical Engineering City University of Hong Kong Kowloon Hong Kong SAR

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Semantic segmentation, a fundamental visual task ubiquitously employed in sectors ranging from transportation and robotics to healthcare, has always captivated the research community. In the wake of rapid advancements in large model research, the foundation model for semantic segmentation tasks, termed the Segment Anything Model (SAM), has been introduced. This model substantially addresses the dilemma of poor generalizability of previous segmentation models and the disadvantage in requiring to retrain the whole model on variant datasets. Nonetheless, segmentation models developed on SAM remain constrained by the inherent limitations of RGB sensors, particularly in scenarios characterized by complex lighting conditions and high-speed motion. Motivated by these observations, a natural recourse is to adapt SAM to additional visual modalities without compromising its robust generalizability. To achieve this, we introduce a lightweight SAM-Event-Adapter (SE-Adapter) module, which incorporates event camera data into a cross-modal learning architecture based on SAM, with only limited tunable parameters incremental. Capitalizing on the high dynamic range and temporal resolution afforded by event cameras, our proposed multi-modal Event-RGB learning architecture effectively augments the performance of semantic segmentation tasks. In addition, we propose a novel paradigm for representing event data in a patch format compatible with transformer-based models, employing multi-spatiotemporal scale encoding to efficiently extract motion and semantic correlations from event representations. Exhaustive empirical evaluations conducted on the DSEC-Semantic and DDD17 datasets provide validation of the effectiveness and rationality of our proposed approach.

关键词： Adaptation models Visualization Semantic segmentation Motion segmentation Transportation Cameras Transformers

来源：评论

学校读者我要写书评

暂无评论

Learning Pixel-wise Continuous Depth Representation via Clustering for Depth Completion

arXiv

引用

arXiv 2024年

作者： Chen, Shenglun Zhang, Hong Ma, Xinzhu Wang, Zhihui Li, Haojie Dalian University of Technology Dalian116620 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Shanghai Artificial Intelligence Laboratory Shanghai AI Lab Shanghai200030 China DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian116620 China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian University of Technology Dalian116620 China

Depth completion is a long-standing challenge in computer vision, where classification-based methods have made tremendous progress in recent years. However, most existing classification-based methods rely on pre-defined pixel-shared and discrete depth values as depth categories. This representation fails to capture the continuous depth values that conform to the real depth distribution, leading to depth smearing in boundary regions. To address this issue, we revisit depth completion from the clustering perspective and propose a novel clustering-based framework called CluDe which focuses on learning the pixel-wise and continuous depth representation. The key idea of CluDe is to iteratively update the pixel-shared and discrete depth representation to its corresponding pixel-wise and continuous counterpart, driven by the real depth distribution. Specifically, CluDe first utilizes depth value clustering to learn a set of depth centers as the depth representation. While these depth centers are pixel-shared and discrete, they are more in line with the real depth distribution compared to pre-defined depth categories. Then, CluDe estimates offsets for these depth centers, enabling their dynamic adjustment along the depth axis of the depth distribution to generate the pixel-wise and continuous depth representation. Extensive experiments demonstrate that CluDe successfully reduces depth smearing around object boundaries by utilizing pixel-wise and continuous depth representation. Furthermore, CluDe achieves state-of-the-art performance on the VOID datasets and outperforms classification-based methods on the KITTI dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Unifying and Improving Graph Convolutional Neural networks with Wavelet Denoising Filters 23

Unifying and Improving Graph Convolutional Neural Networks w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Li, Xiaona Han, Huijin Yan, Xiaoran Sun, Lu Ning, Zhaolong Xia, Feng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Graph convolutional neural network (GCN) is a powerful deep learning framework for network data. However, variants of graph neural architectures can lead to drastically different performance on different tasks. Model comparison calls for a unifying framework with interpretability and principled experimental procedures. Based on the theories from graph signal processing (GSP), we show that GCN's capability is fundamentally limited by the uncertainty principle, and wavelets provide a controllable trade-off between local and global information. We adapt wavelet denoising filters to the graph domain, unifying popular variants of GCN under a common interpretable mathematical framework. Furthermore, we propose WaveThresh and WaveShrink which are novel GCN models based on proven denoising filters from the signal processing literature. Empirically, we evaluate our models and other popular GCNs under a more principled procedure and analyze how trade-offs between local and global graph signals can lead to better performance in different datasets. © 2023 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Speed Master: Quick or Slow Play to Attack Speaker Recognition 39

Speed Master: Quick or Slow Play to Attack Speaker Recogniti...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Zhe Zhang, Wenjie Ren, Ying Kang, Xiangui Yan, Diqun Ma, Bin Wang, Shiqi Guangdong Key Lab of Information Security School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Jinan China Department of Computer Science City University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Backdoor attacks pose a significant threat during the model’s training phase. Attackers craft pre-defined triggers to break deep neural networks, ensuring the model accurately classifies clean samples during inference yet erroneously classifies samples added with these triggers. Recent studies have shown that speaker recognition systems trained on large-scale data are susceptible to backdoor attacks. Existing attackers employ unnoticed ambient sounds as triggers. However, these sounds are not inherently part of the training samples themselves. In essence, triggers can be designed to maintain an intrinsic connection with the original speech to enhance stealthiness. Our paper presents a novel attack methodology named Speed Master, which undermines deep neural networks by manipulating the speed of speech samples. Specifically, we execute poison-only backdoor attacks using speed or tempo adjustment. Changes in speech rate have become a common occurrence, as seen on platforms that allow users to adjust playback speed. In real-world scenarios, people naturally adjust their speaking rate depending on the context. As a result, changes in a speaker’s speech rate are typically perceived as normal and are unlikely to raise suspicion. Furthermore, detecting such subtle adjustments becomes challenging for users without reference speech. Our comprehensive experiments demonstrate that Speed Master can achieve an ASR over 99% in the digital domain, with only a 0.6% poisoning rate. Additionally, we validate the feasibility of Speed Master in the real world and its resistance to typical defensive measures. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability

Divide and Conquer: a Two-Step Method for High Quality Face ...

引用

International Conference on Computer Vision (ICCV)

作者： Yunqian Wen Bo Liu Jingyi Cao Rong Xie Li Song Institute of Image Communication and Network Engineering Shanghai Jiao Tong University School of Computer Science University of Technology Sydney MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University

Face de-identification involves concealing the true identity of a face while retaining other facial characteristics. Current target-generic methods typically disentangle identity features in the latent space, using adversarial training to balance privacy and utility. However, this pattern often leads to a trade-off between privacy and utility, and the latent space remains difficult to explain. To address these issues, we propose IDeudemon, which employs a "divide and conquer" strategy to protect identity and preserve utility step by step while maintaining good explainability. In Step I, we obfuscate the 3D disentangled ID code calculated by a parametric NeRF model to protect identity. In Step II, we incorporate visual similarity assistance and train a GAN with adjusted losses to preserve image utility. Thanks to the powerful 3D prior and delicate generative designs, our approach could protect the identity naturally, produce high quality details and is robust to different poses and expressions. Extensive experiments demonstrate that the proposed IDeudemon outperforms previous state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

8.1 Gbps PAM8 Long-Wave IR FSO Transmission using a 9.15-μm Directly-Modulated QCL with an MCT Detector

8.1 Gbps PAM8 Long-Wave IR FSO Transmission using a 9.15-μm...

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Joharifar, Mahdieh Han, Mengyao Schatz, Richard Puerta, Rafael Sun, Yan-Ting Fan, Yuchuan Maisons, Gregory Abautret, Johan Teissier, Roland Zhang, Lu Spolitis, Sandis Wang, Muguang Bobrovs, Vjaceslavs Lourdudoss, Sebastian Yu, Xianbin Popov, Sergei Ozolins, Oskars Pang, Xiaodan Department of Applied Physics KTH Royal Institute of Technology Stockholm106 91 Sweden Institute of Lightwave Technology Key Lab of All Optical Network & Advanced Telecommunication Network Ministry of Education Beijing Jiaotong University Beijing100044 China Ericsson Research Ericsson AB Stockholm164 83 Sweden RISE Research Institutes of Sweden Kista16440 Sweden MirSense 2 Bd Thomas Gobert Palaiseau91120 France College of Information Science and Electronic Engineering Zhejiang University Zhejiang Lab Hangzhou310027 China Institute of Telecommunications Riga Technical University Riga1048 Latvia Communication Technologies Research Center Riga Technical University Riga1048 Latvia

We experimentally demonstrate a Long-Wave IR FSO link with a 9.15-μm directly modulated quantum cascade laser at room temperature. Up to 8.1 Gb/s PAM8 transmission over 1.4 meter is achieved with a wideband MCT detec... 详细信息

ISBN: (纸本)9781957171180

关键词： Quantum cascade lasers

来源：评论

学校读者我要写书评

暂无评论

Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration

arXiv

引用

arXiv 2024年

作者： Wu, Zhiyuan Sun, Sheng Wang, Yuwei Liu, Min Xu, Ke Pan, Quyang Gao, Bo Wen, Tian The State Key Lab of Processers Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China The Zhongguancun Laboratory Beijing China The Department of Computer Science and Technology Tsinghua University Beijing China The School of Computer Science and Technology The Engineering Research Center of Network Management Technology for High-Speed Railway of Ministry of Education Beijing Jiaotong University Beijing China

The rise of End-Edge-Cloud Collaboration (EECC) offers a promising paradigm for Artificial Intelligence (AI) model training across end devices, edge servers, and cloud data centers, providing enhanced reliability and reduced latency. Hierarchical Federated Learning (HFL) can benefit from this paradigm by enabling multi-tier model aggregation across distributed computing nodes. However, the potential of HFL is significantly constrained by the inherent heterogeneity and dynamic characteristics of EECC environments. Specifically, the uniform model structure bounded by the least powerful end device across all computing nodes imposes a performance bottleneck. Meanwhile, coupled heterogeneity in data distributions and resource capabilities across tiers disrupts hierarchical knowledge transfer, leading to biased updates and degraded performance. Furthermore, the mobility and fluctuating connectivity of computing nodes in EECC environments introduce complexities in dynamic node migration, further compromising the robustness of the training process. To address multiple challenges within a unified framework, we propose End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration (FedEEC), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedEEC introduces two key innovations: (1) Bridge Sample Based Online Distillation Protocol (BSBODP), which enables knowledge transfer between neighboring nodes through generated bridge samples, and (2) Self-Knowledge Rectification (SKR), which refines the transferred knowledge to prevent suboptimal cloud model optimization. The proposed framework effectively handles both cross-tier resource heterogeneity and effective knowledge transfer between neighboring nodes, while satisfying the migration-resilient requirements of EECC. Extensive experiments on three datasets demonstrate that FedEEC achieves significantly hi

关键词： Federated learning

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：