检索结果-内蒙古大学图书馆

A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ji, Zhong Yang, Shuo Liu, Jingren Pang, Yanwei Han, Jungong School of Electrical and Information Engineering Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin University Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Department of Computer Science The University of Sheffield United Kingdom

Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimization of the co-occurrence matrix Ā based on cosine similarity, failing to achieve zero base-novel regions and adequate sparsity in base and novel domains. To address these deficiencies, we propose a Non-Negative Generalized Category Discovery (NN-GCD) framework. It employs Symmetric Non-negative Matrix Factorization (SNMF) as a mathematical medium to prove the equivalence of optimal K-means with optimal SNMF, and the equivalence of SNMF solver with non-negative contrastive learning (NCL) optimization. Utilizing these theoretical equivalences, it reframes the optimization of Ā and K-means clustering as an NCL optimization problem. Moreover, to satisfy the nonnegative constraints and make a GCD model converge to a near-optimal region, we propose a GELU activation function and an NMF NCE loss. To transition Ā from a suboptimal state to the desired Ā∗, we introduce a hybrid sparse regularization approach to impose sparsity constraints. Experimental results show NN-GCD outperforms state-of-the-art methods on GCD benchmarks, achieving an average accuracy of 66.1% on the Semantic Shift Benchmark, surpassing prior counterparts by 4.7%. Copyright © 2024, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

Raformer: Redundancy-Aware Transformer for Video Wire Inpainting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ji, Zhong Su, Yimu Zhang, Yan Hou, Jiacheng Pang, Yanwei Han, Jungong The School of Electrical and Information Engineering Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin University Tianjin300072 China The Shanghai Artificial Intelligence Laboratory Shanghai200232 China The Department of Computer Science The University of Sheffield United Kingdom

Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal. However, wire removal poses greater challenges due to the wires being longer and slimmer than objects typically targeted in general video inpainting tasks, and often intersecting with people and background objects irregularly, which adds complexity to the inpainting process. Recognizing the limitations posed by existing video wire datasets, which are characterized by their small size, poor quality, and limited variety of scenes, we introduce a new VWI dataset with a novel mask generation strategy, namely Wire Removal Video Dataset 2 (WRV2) and Pseudo Wire-Shaped (PWS) Masks. WRV2 dataset comprises over 4,000 videos with an average length of 80 frames, designed to facilitate the development and efficacy of inpainting models. Building upon this, our research proposes the Redundancy-Aware Transformer (Raformer) method that addresses the unique challenges of wire removal in video inpainting. Unlike conventional approaches that indiscriminately process all frame patches, Raformer employs a novel strategy to selectively bypass redundant parts, such as static background segments devoid of valuable information for inpainting. At the core of Raformer is the Redundancy-Aware Attention (RAA) module, which isolates and accentuates essential content through a coarse-grained, window-based attention mechanism. This is complemented by a Soft Feature Alignment (SFA) module, which refines these features and achieves end-to-end feature alignment. Extensive experiments on both the traditional video inpainting datasets and our proposed WRV2 dataset demonstrate that Raformer outperforms other state-of-the-art methods. Our codes and the WRV2 dataset will be made available at: https://***/Suyimu/WRV2. © 2024, CC BY.

关键词： Wire

High-resolution mid-infrared single-photon upconversion ranging

学校读者我要写书评

暂无评论

Photonics Research 2024年第6期12卷 1294-1302页

作者： SHUHONG JIANG KUN HUANG TINGTING YU JIANAN FANG BEN SUN YAN LIANG QIANG HAO E.WU MING YAN HEPING ZENG State Key Laboratory of Precision Spectroscopy East China Normal UniversityShanghai 200062China Chongqing Key Laboratory of Precision Optics Chongqing Institute of East China Normal UniversityChongqing 401121China Collaborative Innovation Center of Extreme Optics Shanxi UniversityTaiyuan 030006China School of Optical Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Shanghai Research Center for Quantum Sciences Shanghai 201315China Guangyang Bay Laboratory Chongqing Institute for Brain and IntelligenceChongqing 400064China

Single-photon laser ranging has widespread applications in remote sensing and target ***,highly sensitive light detection and ranging(lidar)has long been restricted in the visible or near-infrared *** appealing quest is to extend the operation wavelength into the mid-infrared(MIR)region,which calls for an infrared photon-counting system at high detection sensitivity and precise temporal ***,we devise and demonstrate an MIR upconversion lidar based on nonlinear asynchronous optical ***,the infrared probe is interrogated in a nonlinear crystal by a train of pump pulses at a slightly different repetition rate,which favors temporal optical scanning at a picosecond timing resolution and a kilohertz refreshing rate ***,the cross-correlation upconversion trace is temporally stretched by a factor of 2×10^(4),which can thus be recorded by a low-bandwidth silicon *** combination with the time-correlated photon-counting technique,the achieved effective resolution is about two orders of magnitude better than the timing jitter of the detector itself,which facilitates a ranging precision of 4μm under a low detected flux of 8×10^(−5) photons per *** presented MIR time-of-flight range finder is featured with single-photon sensitivity and high positioning resolution,which would be particularly useful in infrared sensing and imaging in photon-starved scenarios.

关键词： resolution lidar repetition

KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing

学校读者我要写书评

暂无评论

KE-GAN: Knowledge Embedded Generative Adversarial Networks f...

IEEE/CVF Conference on computer Vision and Pattern Recognition

作者： Mengshi Qi Yunhong Wang Jie Qin Annan Li State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Inception Institute of Artificial Intelligence UAE

In recent years, scene parsing has captured increasing attention in computer vision. Previous works have demonstrated promising performance in this task. However, they mainly utilize holistic features, whilst neglecting the rich semantic knowledge and inter-object relationships in the scene. In addition, these methods usually require a large number of pixel-level annotations, which is too expensive in practice. In this paper, we propose a novel Knowledge Embedded Generative Adversarial Networks, dubbed as KE-GAN, to tackle the challenging problem in a semi-supervised fashion. KE-GAN captures semantic consistencies of different categories by devising a Knowledge Graph from the large-scale text corpus. In addition to readily-available unlabeled data, we generate synthetic images to unveil rich structural information underlying the images. Moreover, a pyramid architecture is incorporated into the discriminator to acquire multi-scale contextual information for better parsing results. Extensive experimental results on four standard benchmarks demonstrate that KE-GAN is capable of improving semantic consistencies and learning better representations for scene parsing, resulting in the state-of-the-art performance.

关键词：

Distinct neural networks of emotional valence and uncertainty in the human amygdala underlying different mental disorders

学校读者我要写书评

暂无评论

science Bulletin 2025年

作者： Xiang, Shitong Xie, Chao Xiao, Xiao Banaschewski, Tobias Barker, Gareth J. Bokde, Arun L.W. Flor, Herta Grigis, Antoine Garavan, Hugh Gowland, Penny Heinz, Andreas Brühl, Rüdiger Martinot, Jean-Luc Martinot, Marie-Laure Paillère Penttilä, Jani Artiges, Eric Nees, Frauke Orfanos, Dimitri Papadopoulos Poustka, Luise Hohmann, Sarah Holz, Nathalie Baeuchl, Christian Smolka, Michael N. Vaidya, Nilakshi Walter, Henrik Whelan, Robert Bobou, Marina Broulidakis, John van Noort, Betteke Maria Stringaris, Argyris Zhang, Zuo Robinson, Lauren Winterer, Jeanne Zhang, Yuning King, Sinead Schmidt, Ulrike Sinclair, Julia Desrivières, Sylvane Schumann, Gunter Becker, Benjamin Robbins, Trevor W. Jia, Tianye Feng, Jianfeng Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China Ministry of Education Shanghai200433 China Behavioral and Cognitive Neuroscience Center Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China Ministry of Education Frontiers Center for Brain Science Fudan University Shanghai200433 China Department of Child and Adolescent Psychiatry and Psychotherapy Central Institute of Mental Health Medical Faculty Mannheim Heidelberg University Mannheim68159 Germany Department of Neuroimaging Institute of Psychiatry Psychology & Neuroscience King's College London WC2R 2LS United Kingdom Discipline of Psychiatry School of Medicine and Trinity College Institute of Neuroscience Trinity College Dublin DublinD02 PN40 Iceland Institute of Cognitive and Clinical Neuroscience Central Institute of Mental Health Medical Faculty Mannheim Heidelberg University Square J5 Mannheim68159 Germany Department of Psychology School of Social Sciences University of Mannheim Mannheim68131 Germany NeuroSpin CEA Université Paris-Saclay Gif-sur-Yvette91191 France Departments of Psychiatry and Psychology University of Vermont BurlingtonVT05405 United States Sir Peter Mansfield Imaging Centre School of Physics and Astronomy University of Nottingham University Park NottinghamNG7 2RD United Kingdom Department of Psychiatry and Psychotherapy CCM Charité – Universitätsmedizin Berlin Corporate Member of Freie Universität Berlin Humboldt-Universität zu Berlin and Berlin Institute of Health Berlin10117 Germany Berlin10587 Germany Université Paris-Saclay Université Paris Cité INSERM U1299"Trajectoires Développementales & Psychiatrie" Ecole Normale Supérieure Paris-Saclay Centre Borelli CNRS UMR9010 Gif-sur-Yvette91191 France AP-HP.Sorbonne Université Department of Child and Adolescent Psychiatry Pitié-Salpêtrière Hospital Paris75013 France Department of Social and Health Care

Transfer Learning for EEG-Based brain-computer interfaces: A Review of Progress Made Since 2016

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wu, Dongrui Xu, Yifan Lu, Bao-Liang The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Brain Science and Technology Research Center Qing Yuan Research Institute Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai200240 China

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. The most common non-invasive BCI modality, electroencephalogram (EEG), is sensitive to noise/artifact and suffers between-subject/within-subject non-stationarity. Therefore, it is difficult to build a generic pattern recognition model in an EEG-based BCI system that is optimal for different subjects, during different sessions, for different devices and tasks. Usually, a calibration session is needed to collect some training data for a new subject, which is time-consuming and user unfriendly. Transfer learning (TL), which utilizes data or knowledge from similar or relevant subjects/sessions/devices/tasks to facilitate learning for a new subject/session/device/task, is frequently used to reduce the amount of calibration effort. This paper reviews journal publications on TL approaches in EEG-based BCIs in the last few years, i.e., since 2016. Six paradigms and applications - motor imagery, event-related potentials, steady-state visual evoked potentials, affective BCIs, regression problems, and adversarial attacks - are considered. For each paradigm/application, we group the TL approaches into cross-subject/session, cross-device, and cross-task settings and review them separately. Observations and conclusions are made at the end of the paper, which may point to future research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： brain computer interface

Hermes: A fast cross-ISA binary translator with post-optimization 15

学校读者我要写书评

暂无评论

Hermes: A fast cross-ISA binary translator with post-optimiz...

International Symposium on Code Generation and Optimization (CGO)

作者： Xiaochun Zhang Qi Guo Yunji Chen Tianshi Chen Weiwu Hu Loongson Technology Corporation Limited Beijing China State Key Laboratory of Computer Architecture Chinese Academy of Sciences Beijing China Carnegie Mellon University Pittsburgh PA USA Center for Excellence in Brain Science CAS

ISBN: (纸本)9781479981618

In the era of mobile and cloud computing, cross-ISA (Instruction Set Architecture) binary translation attracts increasing attentions due to the ISA diversity of computing platforms. To easily adapt to vast guest- and host-ISAs with minimal porting efforts, existing cross-ISA binary translators (e.g., QEMU) are typically built upon ISA-independent Intermediate Representation (IR). Although IR conceals the architectural details of different IS As, it also prevents enforcing several effective ISA-specific optimizations, which results in severe performance degradation. To improve the performance of cross-ISA binary translation without loss of portability, we present a fast cross-ISA binary translator, Hermes, by conducting post-optimization on the translated code, rather than on the IR as conventional binary translators do. The proposed post-optimization technique uses Host-specific Data Dependence Graph (HDDG) to significantly eliminate redundant instructions, including arithmetic, load/store and call/return-emulation instructions. To validate our approach, we implement Hermes on a commercial MIPS host system for both ×86 and ARM guest. Compared with QEMU dynamic binary translator, HERMES improves the performance by a factor of 3.14× and 5.18× for ×86 and ARM guest, respectively. Compared with state-of-the-art static binary translator, HERMES achieves comparable performance, while it reduces the translation overhead by 185×.

关键词： Optimization Registers Emulation Mobile communication Cloud computing Program processors computer architecture

Tolerating Device-to-Device Variation for Memristive Crossbar-Based Neuromorphic Computing Systems: A New Bayesian Perspective

学校读者我要写书评

暂无评论

Tolerating Device-to-Device Variation for Memristive Crossba...

International Joint Conference on Neural Networks (IJCNN)

作者： Yang Xiao Qi Xu Bo Yuan Research Institute of Trustworthy Autonomous System (RITAS) Southern University of Science and Technology (SUSTech) Shenzhen China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology (SUSTech) Shenzhen China School of Microelectronics University of Science and Technology of China (USTC)

Memristive crossbar-based architecture provides an energy-efficient platform to accelerate neural networks (NNs) thanks to its Processing-in-Memory (PIM) nature. However, the device-to-device variation (DDV), which is typically modeled as Lognormal distribution, deviates the programmed weights from their target values, resulting in significant performance degradation. This paper proposes a new Bayesian Neural Network (BNN) approach to enhance the robustness of weights against DDV. Instead of using the widely-used Gaussian variational posterior in conventional BNNs, our approach adopts a DDV-specific variational posterior distribution, i.e., Lognormal distribution. Accordingly, in the new BNN approach, the prior distribution is modified to keep consistent with the posterior distribution to avoid expensive Monte Carlo simulations. Furthermore, the mean of the prior distribution is dynamically adjusted in accordance with the mean of the Lognormal variational posterior distribution for better convergence and accuracy. Compared with the state-of-the-art approaches, experimental results show that the proposed new BNN approach can significantly boost the inference accuracy with the consideration of DDV on several well-known datasets and modern NN architectures. For example, the inference accuracy can be improved from 18% to 74% in the scenario of ResNet-18 on CIFAR-10 even under large variations.

关键词：

Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lu, Ning Liu, Shengcai Zhang, Zhirui Wang, Qi Liu, Haifeng Tang, Ke Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Centre for Frontier AI Research Agency for Science Technology and Research Singapore Tencent AI Lab China Department of Computer Science and Engineering Southern University of Science and Technology China OPPO Mobile Telecommunications Corp China

Word-level textual adversarial attacks have demonstrated notable efficacy in misleading Natural Language Processing (NLP) models. Despite their success, the underlying reasons for their effectiveness and the fundamental characteristics of adversarial examples (AEs) remain obscure. This work aims to interpret word-level attacks by examining their n-gram frequency patterns. Our comprehensive experiments reveal that in approximately 90% of cases, word-level attacks lead to the generation of examples where the frequency of n-grams decreases, a tendency we term as the n-gram Frequency Descend (nFD). This finding suggests a straightforward strategy to enhance model robustness: training models using examples with n-FD. To examine the feasibility of this strategy, we employed the ngram frequency information, as an alternative to conventional loss gradients, to generate perturbed examples in adversarial training. The experiment results indicate that the frequency-based approach performs comparably with the gradient-based approach in improving model robustness. Our research offers a novel and more intuitive perspective for understanding word-level textual adversarial attacks and proposes a new direction to improve model robustness. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics