检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wei, Hui Wang, Zhixiang Jia, Xuemei Zheng, Yinqiang Tang, Hao Satoh, Shin'ichi Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering China The University of Tokyo Japan RIISE Japan National Institute of Informatics Japan CVL ETH Zurich Switzerland

Adversarial attacks on thermal infrared imaging expose the risk of related applications. Estimating the security of these systems is essential for safely deploying them in the real world. In many cases, realizing the attacks in the physical space requires elaborate special perturbations. These solutions are often impractical and attention-grabbing. To address the need for a physically practical and stealthy adversarial attack, we introduce HOTCOLD Block, a novel physical attack for infrared detectors that hide persons utilizing the wearable Warming Paste and Cooling Paste. By attaching these readily available temperature-controlled materials to the body, HOTCOLD Block evades human eyes efficiently. Moreover, unlike existing methods that build adversarial patches with complex texture and structure features, HOTCOLD Block utilizes an SSP-oriented adversarial optimization algorithm that enables attacks with pure color blocks and explores the influence of size, shape, and position on attack performance. Extensive experimental results in both digital and physical environments demonstrate the performance of our proposed HOTCOLD Block. Code is available: https://***/weihui1308/HOTCOLDBlock. © 2022, CC BY.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking

arXiv

引用

arXiv 2022年

作者： Fischer, Tobias Huang, Thomas E. Pang, Jiangmiao Qiu, Linlu Chen, Haofeng Darrell, Trevor Yu, Fisher The Department of Information Technology and Electrical Engineering ETH Zurich Switzerland The Shanghai AI Laboratory China The Department of EECS Massachusetts Institute of Technology United States The Computer Science Department Stanford University United States The Department of EECS UC Berkeley United States

Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions in images. In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning. We combine this similarity learning with multiple existing object detectors to build Quasi-Dense Tracking (QDTrack), which does not require displacement regression or motion priors. We find that the resulting distinctive feature space admits a simple nearest neighbor search at inference time for object association. In addition, we show that our similarity learning scheme is not limited to video data, but can learn effective instance similarity even from static input, enabling a competitive tracking performance without training on videos or using tracking supervision. We conduct extensive experiments on a wide variety of popular MOT benchmarks. We find that, despite its simplicity, QDTrack rivals the performance of state-of-the-art tracking methods on all benchmarks and sets a new state-of-the-art on the large-scale BDD100K MOT benchmark, while introducing negligible computational overhead to the detector. Copyright © 2022, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

SteGANomaly: Inhibiting CycleGAN Steganography for Unsupervised Anomaly Detection in Brain MRI 23rd

SteGANomaly: Inhibiting CycleGAN Steganography for Unsupervi...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Baur, Christoph Graf, Robert Wiestler, Benedikt Albarqouni, Shadi Navab, Nassir TU Munich Munich Germany Computer Vision Laboratory ETH Zurich Zurich Switzerland Whiting School of Engineering Johns Hopkins University Baltimore United States Department of Neuroradiology Klinikum rechts der Isar TU Munich Munich Germany

ISBN: (纸本)9783030597122

Recently, it has been shown that CycleGANs are masters of steganography. They cannot only learn reliable mappings between two distributions without calling for paired training data, but can effectively hide information unseen during training in mapping results from which input data can be recovered almost perfectly. When preventing this during training, CycleGANs actually map samples much closer to the training distribution. Here, we propose to leverage this effect in the context of trending unsupervised anomaly detection, which primarily relies on modeling healthy anatomy with generative models. Here, we embed anomaly detection into a CycleGAN-based style-transfer framework, which is trained to translate healthy brain MR images to a simulated distribution with lower entropy and vice versa. By filtering high frequency, low amplitude signals from lower entropy samples during training, the resulting model suppresses anomalies in reconstructions of the input data at test time. Similar to Autoencoder and GAN-based anomaly detection methods, this allows us to delineate pathologies directly from residuals between input and reconstruction. Various ablative studies and comparisons to state-of-the-art methods highlight the potential of our method. © 2020, Springer Nature Switzerland AG.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Scaling and logic in the color code on a superconducting quantum processor

arXiv

引用

arXiv 2024年

作者： Lacroix, Nathan Bourassa, Alexandre Heras, Francisco J.H. Zhang, Lei M. Bausch, Johannes Senior, Andrew W. Edlich, Thomas Shutty, Noah Sivak, Volodymyr Bengtsson, Andreas McEwen, Matt Higgott, Oscar Kafri, Dvir Claes, Jahan Morvan, Alexis Chen, Zijun Zalcman, Adam Madhuk, Sid Acharya, Rajeev Beni, Laleh Aghababaie Aigeldinger, Georg Alcaraz, Ross Andersen, Trond I. Ansmann, Markus Arute, Frank Arya, Kunal Asfaw, Abraham Atalaya, Juan Babbush, Ryan Ballard, Brian Bardin, Joseph C. Bilmes, Alexander Blackwell, Sam Bovaird, Jenna Bowers, Dylan Brill, Leon Broughton, Michael Browne, David A. Buchea, Brett Buckley, Bob B. Burger, Tim Burkett, Brian Bushnell, Nicholas Cabrera, Anthony Campero, Juan Chang, Hung-Shen Chiaro, Ben Chih, Liang-Ying Cleland, Agnetta Y. Cogan, Josh Collins, Roberto Conner, Paul Courtney, William Crook, Alexander L. Curtin, Ben Das, Sayan Demura, Sean De Lorenzo, Laura Di Paolo, Agustin Donohoe, Paul Drozdov, Ilya Dunsworth, Andrew Eickbusch, Alec Elbag, Aviv Moshe Elzouka, Mahmoud Erickson, Catherine Ferreira, Vinicius S. Burgos, Leslie Flores Forati, Ebrahim Fowler, Austin G. Foxen, Brooks Ganjam, Suhas Garcia, Gonzalo Gasca, Robert Genois, Élie Giang, William Gilboa, Dar Gosula, Raja Dau, Alejandro Grajales Graumann, Dietrich Greene, Alex Gross, Jonathan A. Ha, Tan Habegger, Steve Hansen, Monica Harrigan, Matthew P. Harrington, Sean D. Heslin, Stephen Heu, Paula Hiltermann, Reno Hilton, Jeremy Hong, Sabrina Huang, Hsin-Yuan Huff, Ashley Huggins, William J. Jeffrey, Evan Jiang, Zhang Jin, Xiaoxuan Joshi, Chaitali Juhas, Pavol Kabel, Andreas Kang, Hui Karamlou, Amir H. Kechedzhi, Kostyantyn Khaire, Trupti Khattar, Tanuj Khezri, Mostafa Kim, Seon Klimov, Paul V. Kobrin, Bryce Korotkov, Alexander N. Kostritsa, Fedor Kreikebaum, John Mark Kurilovich, Vladislav D. Landhuis, David Lange-Dei, Tiano Langley, Brandon W. Laptev, Pavel Lau, Kim-Ming Ledford, Justin Lee, Kenny Lester, Brian J. Le Guevel, Loïck Li, Wing Yan Li, Yin Lill, Alexander T. Livingston, William P. Locharla, Aditya Lucero, Erik L Google Research Mountain ViewCA United States Department of Physics ETH Zurich Switzerland Google DeepMind London United Kingdom Department of Electrical and Computer Engineering University of Massachusetts AmherstMA United States Department of Physics University of Connecticut StorrsCT United States Department of Computer Science University of California Santa BarbaraCA United States Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Department of Physics Massachusetts Institute of Technology CambridgeMA United States

Quantum error correction [1-6] is essential for bridging the gap between the error rates of physical devices and the extremely low logical error rates required for quantum algorithms. Recent error-correction demonstrations on superconducting processors [7-13] have focused primarily on the surface code [14], which offers a high error threshold but poses limitations for logical operations. In contrast, the color code [15] enables much more efficient logic, although it requires more complex stabilizer measurements and decoding techniques. Measuring these stabilizers in planar architectures such as superconducting qubits is challenging, and so far, realizations of color codes [16-24] have not addressed performance scaling with code size on any platform. Here, we present a comprehensive demonstration of the color code on a superconducting processor [12], achieving logical error suppression and performing logical operations. Scaling the code distance from three to five suppresses logical errors by a factor of Λ3/5 = 1.56(4). Simulations indicate this performance is below the threshold of the color code, and furthermore that the color code may be more efficient than the surface code with modest device improvements. Using logical randomized benchmarking [25], we find that transversal Clifford gates add an error of only 0.0027(3), which is substantially less than the error of an idling error correction cycle. We inject magic states [26], a key resource for universal computation, achieving fidelities exceeding 99 % with post-selection (retaining about 75 % of the data). Finally, we successfully teleport logical states between distance-three color codes using lattice surgery [27], with teleported state fidelities between 86.5(1) % and 90.7(1) %. This work establishes the color code as a compelling research direction to realize fault-tolerant quantum computation on superconducting processors in the near future. © 2024, CC BY.

关键词： Color codes

来源：评论

学校读者我要写书评

暂无评论

Automated Pollen Detection with an Affordable Technology 20

Automated Pollen Detection with an Affordable Technology

引用

Proceedings of the 2020 International Conference on Embedded Wireless Systems and networks

作者： Nam Cao Matthias Meyer Lothar Thiele Olga Saukh Institute of Technical Informatics Graz University of Technology Austria Computer Engineering and Networks Lab ETH Zurich Switzerland

ISBN: (纸本)9780994988645

Airborne pollen cause seasonal allergies and the number of people affected increases yearly due to global warming and urbanization. Governmental pollen sensing stations are sampling traps which require manual pollen identification and counting by trained personnel in the lab. In the past years, a number of researchers and startups started working towards automated pollen measurements by exploring a wide range of techniques. Many solutions reported in the literature are expensive or work for a limited number of pollen species. In this paper, we present the design of a prototype of an automated and affordable pollen detection device built from off-the-shelf components. The design consists of three subsystems operating in the field and communicating the data to the backend server: (1) a particle trap with automatic filtering, (2) a particle concentration subsystem, and (3) a digital transmitted light microscope with layer-wise focus. The prototype shows effective particle gathering, filtering and concentration in a tiny-sized area. As a result, we reduce particle loss and improve image quality taken by the optical system when searching and focusing on pollen grains. The test results show that our device achieves high efficiency with up to 150 l/min air flow rates, evaluates over 90 % of captured pollen grains, and achieves 1 h measurement delay on average (2 h at maximum). The prototype collects raw time-stamped microscopic images of pollen with 5-60 depth layers per sample depending on the number of objects contained in one sample. All images are transmitted to the backend server where we run a pollen detection algorithm to extract individual pollen grains from every image. We achieve 0.90 average precision and F1-score of 0.88 when detecting pollen in the images of individual layers taken in the field. Our prototype successfully operated in the wild for 115 days between April and August 2019, and shows high stability under a wide range of varying weather conditions,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI 23rd

Scale-Space Autoencoders for Unsupervised Anomaly Segmentati...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Baur, Christoph Wiestler, Benedikt Albarqouni, Shadi Navab, Nassir TU Munich Munich Germany Computer Vision Laboratory ETH Zurich Zurich Switzerland Whiting School of Engineering Johns Hopkins University Baltimore United States Department of Diagnostic and Interventional Neuroradiology Klinikum rechts der Isar TU Munich Munich Germany

ISBN: (纸本)9783030597184

Brain pathologies can vary greatly in size and shape, ranging from few pixels (i.e. MS lesions) to large, space-occupying tumors. Recently proposed Autoencoder-based methods for unsupervised anomaly segmentation in brain MRI have shown promising performance, but face difficulties in modeling distributions with high fidelity, which is crucial for accurate delineation of particularly small lesions. Here, similar to these previous works, we model the distribution of healthy brain MRI to localize pathologies from erroneous reconstructions. However, to achieve improved reconstruction fidelity at higher resolutions, we learn to compress and reconstruct different frequency bands of healthy brain MRI using the laplacian pyramid. In a range of experiments comparing our method to different State-of-the-Art approaches on three different brain MR datasets with MS lesions and tumors, we show improved anomaly segmentation performance and the general capability to obtain much more crisp reconstructions of input data at native resolution. The modeling of the laplacian pyramid further enables the delineation and aggregation of lesions at multiple scales, which allows to effectively cope with different pathologies and lesion sizes using a single model. © 2020, Springer Nature Switzerland AG.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Demo Abstract: A Testbed for Long-Range LoRa Communication

Demo Abstract: A Testbed for Long-Range LoRa Communication

引用

International Symposium on Information Processing in Sensor networks (IPSN)

作者： Roman Trüb Reto Da Forno Tonia Gsell Jan Beutel Lothar Thiele ETH Zurich Computer Engineering and Networks Laboratory Zurich Switzerland

ISBN: (纸本)9781728107271

Designing and testing low-power wireless communication protocols often requires experimental deployments on real hardware in realistic settings. Infrastructure testbeds have the advantage that they allow reproducible results using different network configurations. However, most testbeds are either in- or outdoor only and do not span long and short ranges at the same time. In this work, we present an extension to the popular FlockLab testbed on a campus-scale in order to better support testing of long-range communciation, for example using the LoRa modulation. Different to existing LoRa test networks where specific protocol layers are fixed, we support custom modification above the physical hardware (above PHY) which allows the development and testing of alternative full custom MAC layers that are not based on LoRaWan.

关键词： Synchronization Observers Global Positioning System Protocols Wireless communication Testing Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition

arXiv

引用

arXiv 2022年

作者： Burrello, Alessio Morghet, Francesco Bianco Scherer, Moritz Benatti, Simone Benini, Luca Macii, Enrico Poncino, Massimo Pagliari, Daniele Jahier DEI Università di Bologna Bologna Italy Department of Control and Computer Engineering Politecnico di Torino Turin Italy Integrated Systems Laboratory ETH Zurich Switzerland Department of Sciences and Methods for Engineering University of Modena and Reggio Emilia Italy Interuniversity Department of Regional and Urban Studies and Planning Politecnico di Torino Turin Italy

Human-machine interaction is gaining traction in rehabilitation tasks, such as controlling prosthetic hands or robotic arms. Gesture recognition exploiting surface electromyographic (sEMG) signals is one of the most promising approaches, given that sEMG signal acquisition is non-invasive and is directly related to muscle contraction. However, the analysis of these signals still presents many challenges since similar gestures result in similar muscle contractions. Thus the resulting signal shapes are almost identical, leading to low classification accuracy. To tackle this challenge, complex neural networks are employed, which require large memory footprints, consume relatively high energy and limit the maximum battery life of devices used for classification. This work addresses this problem with the introduction of the Bioformers. This new family of ultra-small attention-based architectures approaches state-of-the-art performance while reducing the number of parameters and operations of 4.9×. Additionally, by introducing a new inter-subjects pre-training, we improve the accuracy of our best Bioformer by 3.39%, matching state-of-the-art accuracy without any additional inference cost. Deploying our best performing Bioformer on a Parallel, Ultra-Low Power (PULP) microcontroller unit (MCU), the GreenWaves GAP8, we achieve an inference latency and energy of 2.72 ms and 0.14 mJ, respectively, 8.0× lower than the previous state-of-the-art neural network, while occupying just 94.2 kB of memory. © 2022, CC BY-SA.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Demo Abstract: The Dual Processor Platform Architecture

Demo Abstract: The Dual Processor Platform Architecture

引用

International Symposium on Information Processing in Sensor networks (IPSN)

作者： Jan Beutel Roman Trüb Reto Da Forno Markus Wegmann Tonia Gsell Romain Jacob Michael Keller Felix Sutton Lothar Thiele ETH Zurich Computer Engineering and Networks Laboratory Zurich Switzerland

ISBN: (纸本)9781728107271

In this demo we will demonstrate an implementation of the Event-based Low-power Wireless Bus (eLWB) based on an FSK version of Glossy for the CC430. The application is an event-triggered geophone platform that uses the CC430 ComBoard and eLWB. This application generates periodic as well as event-based traffic that is transmitted using eLWB to a central sink (base station) running on a laptop. Different network traffic patterns can be observed depending on the behavior of the application w.r.t. the sensed data. Users can interact with the demo by generating seismic events (shaking, knocking, footsteps etc.). Furthermore, we will showcase our field deployments in the Swiss Alps based on the online web interface.

关键词： Wireless sensor networks Wireless communication Fasteners Software Random access memory computer architecture Information processing

来源：评论

学校读者我要写书评

暂无评论

Demo Abstract: How Many Climb the Matterhorn?

Demo Abstract: How Many Climb the Matterhorn?

引用

International Symposium on Information Processing in Sensor networks (IPSN)

作者： Matthias Meyer Timo Farei-Campagna Akos Pasztor Reto Da Forno Tan Beutel Lothar Thiele ETH Zurich Computer Engineering and Networks Laboratory Zurich Switzerland

ISBN: (纸本)9781728107271

In this demo abstract we present a custom-built low-power geophone sensor node which features on-device mountaineer classification using a convolutional neural network. The execution of such a processing-heavy algorithm on an embedded platform is enabled by optimizing the memory requirement of the neural network through advanced quantization and pipelining techniques. As a result, real-time classification with low energy consumption can be achieved.

关键词： Convolutional neural networks Hazards Memory management Wireless sensor networks Streaming media Monitoring

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：