检索结果-内蒙古大学图书馆

Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

Context Decoupling Augmentation for Weakly Supervised Semant...

International Conference on Computer Vision (ICCV)

作者： Yukun Su Ruizhou Sun Guosheng Lin Qingyao Wu School of Software and Engineering South China University of Technology Key Laboratory of Big Data and Intelligent Robot Ministry of Education School of Computer Science and Engineering Nanyang Technological University

ISBN: (纸本)9781665428132

data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that has been deeply studied in recent years, conventional data augmentation approaches for WSSS usually employ geometrical transformations, random cropping and color jittering. However, merely increasing the same contextual semantic data does not bring much gain to the networks to distinguish the objects, e.g., the correct image-level classification of "aeroplane" may be not only due to the recognition of the object itself, but also its co-occurrence context like "sky", which will cause the model to focus less on the object features. To this end, we present a Context Decoupling Augmentation (CDA) method, to change the inherent context in which the objects appear and thus drive the network to remove the dependence between object instances and contextual information. To validate the effectiveness of the proposed method, extensive experiments on PASCAL VOC 2012 and COCO datasets with several alternative network architectures demonstrate that CDA can boost various popular WSSS methods to the new state-of-the-art by a large margin. Code is available at https://***/suyukun666/CDA

关键词： Training Deep learning Image segmentation Image recognition Image color analysis Semantics Neural networks

GAN-based Intrusion Detection data Enhancement

学校读者我要写书评

暂无评论

GAN-based Intrusion Detection Data Enhancement

第33届中国控制与决策会议

作者： Wei Fu Liping Qian Xiaohui Zhu School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture

In view of the lack of intrusion detection data and the slow update of mainstream detection methods,an intrusion detection data generation method based on a generative adversarial network is ***,the overall data is digitized and normalized to maintain the integrity of the data;Then use the ACGAN model to learn the hidden features of the data and generate new data;Finally,evaluate the similarity and validity of the generated data from multiple *** results show that the data generated by this method has similar characteristics to the original data,and can be used to enhance the original data set to meet the needs of intrusion detection systems.

关键词： Smart City Cyber Security Intrusion Detection data Generative Adversarial Network

Learning defense transformers for counterattacking adversarial examples

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Jincheng Cao, Jiezhang Zhang, Yifan Chen, Jian Tan, Mingkui South China University of Technology China ETH Zürich Switzerland National University of Singapore Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China

Deep neural networks (DNNs) are vulnerable to adversarial examples with small perturbations. Adversarial defense thus has been an important means which improves the robustness of DNNs by defending against adversarial examples. Existing defense methods focus on some specific types of adversarial examples and may fail to defend well in real-world applications. In practice, we may face many types of attacks where the exact type of adversarial examples in real-world applications can be even unknown. In this paper, motivated by that adversarial examples are more likely to appear near the classification boundary, we study adversarial examples from a new perspective that whether we can defend against adversarial examples by pulling them back to the original clean distribution. We theoretically and empirically verify the existence of defense affine transformations that restore adversarial examples. Relying on this, we learn a defense transformer to counterattack the adversarial examples by parameterizing the affine transformations and exploiting the boundary information of DNNs. Extensive experiments on both toy and real-world datasets demonstrate the effectiveness and generalization of our defense transformer. Copyright © 2021, The Authors. All rights reserved.

关键词： Network security

Vehicle Segmentation with Coarse Distance Estimation Based on Monocular Vision

学校读者我要写书评

暂无评论

Vehicle Segmentation with Coarse Distance Estimation Based o...

IEEE International Conference on e-Business Engineering (ICEBE)

作者： Fangyuan Xie Pengshuai Yin Zehui Ke Ruizhou Sun Ke Ding Jian Chen Qingyao Wu School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Pazhou Lab Guangzhou China

ISBN: (纸本)9781665444194

With the increasing population of drivers and the popularity of intelligent cars, traffic safety is becoming more concerned. Aiming to reduce the probability of road accidents, many works have explored how to provide an early warning when the distances between the current car (or the in-car camera) and vehicles ahead are dangerous. In this paper, benefiting from the robust pixel-level understanding of cutting-edge deep networks, we introduce a vehicle segmentation method based on monocular vision, detecting vehicles in front of the current one and generating a segmentation mask for each vehicle instance detected. Instead of concentrating our efforts on measuring distance precisely, we categorize distances into three classes (“near”, “medium”, and “far”), which are pretty enough for an early collision warning. Our model is trained and evaluated on our hand-made dataset, after which we transfer and deploy it onto an Android TV virtual machine to test its performance. All the results we got show that our method does a good job in vehicle segmentation with coarse distance estimation, being applicable to aided driving.

关键词： TV Sociology Estimation Cameras Virtual machining Safety Automobiles

LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Jingwei Wang, Chuansheng Huang, Jiayan Fan, Haoyi Grau, Antoni Zhang, Fuquan The College of Computer and Big Data Fuzhou University Fuzhou China The Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain The New Engineering Industry College Putian University Putian China School of Computer and Artificial Intelligence Zhengzhou University China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Control Engineering Minjiang University Fuzhou China Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu China Fuzhou Technology Innovation Center of Intelligent Manufacturing information System Minjiang University Fuzhou China Fujian Polytechnic Normal University Fujian Province University Fuzhou China

Driver drowsiness electroencephalography (EEG) signal monitoring can timely alert drivers of their drowsiness status, thereby reducing the probability of traffic accidents. Graph convolutional networks (GCNs) have shown significant advancements in processing the non-stationary, time-varying, and non-Euclidean nature of EEG signals. However, the existing single-channel EEG adjacency graph construction process lacks interpretability, which hinders the ability of GCNs to effectively extract adjacency graph features, thus affecting the performance of drowsiness monitoring. To address this issue, we propose an edge-end lightweight dual graph convolutional network (LDGCN). Specifically, we are the first to incorporate neurophysiological knowledge to design a Baseline Drowsiness Status Adjacency Graph (BDSAG), which characterizes driver drowsiness status. Additionally, to express more features within limited EEG data, we introduce the Augmented Graph-level Module (AGM). This module captures global and local information at the graph level, ensuring that BDSAG features remain intact while enhancing effective feature expression capability. Furthermore, to deploy our method on the fourth-generation Raspberry Pi, we utilize Adaptive Pruning Optimization (APO) on both channels and neurons, reducing inference latency by almost half. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization compared to existing state-of-the-art algorithms. All our source code can be found at https://***/BryantDom/Driver-Drowsiness-Monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

Self-supervised 3D Skeleton Action Representation Learning with Motion Consistency and Continuity

学校读者我要写书评

暂无评论

Self-supervised 3D Skeleton Action Representation Learning w...

International Conference on Computer Vision (ICCV)

作者： Yukun Su Guosheng Lin Qingyao Wu School of Software and Engineering South China University of Technology Key Laboratory of Big Data and Intelligent Robot Ministry of Education School of Computer Science and Engineering Nanyang Technological University

ISBN: (纸本)9781665428132

Recently, self-supervised learning (SSL) has been proved very effective and it can help boost the performance in learning representations from unlabeled data in the image domain. Yet, very little is explored about its usefulness in 3D skeleton-based action recognition understanding. Directly applying existing SSL techniques for 3D skeleton learning, however, suffers from trivial solutions and imprecise representations. To tackle these drawbacks, we consider perceiving the consistency and continuity of motion at different playback speeds are two critical issues. To this end, we propose a novel SSL method to learn the 3D skeleton representation in an efficacious way. Specifically, by constructing a positive clip (speed-changed) and a negative clip (motion-broken) of the sampled action sequence, we encourage the positive pairs closer while pushing the negative pairs to force the network to learn the intrinsic dynamic motion consistency information. Moreover, to enhance the learning features, skeleton interpolation is further exploited to model the continuity of human skeleton data. To validate the effectiveness of the proposed method, extensive experiments are conducted on Kinetics, NTU60, NTU120, and PKUMMD datasets with several alternative network architectures. Experimental evaluations demonstrate the superiority of our approach and through which, we can gain significant performance improvement without using extra labeled data.

关键词： Representation learning Interpolation Three-dimensional displays Dynamics Transfer learning Force Network architecture

SFF-DA: Sptialtemporal Feature Fusion for Detecting Anxiety Nonintrusively

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mo, Haimiao Li, Yuchen Yang, Shanlin Zhang, Wei Ding, Shuai The School of Management Hefei University of Technology Anhui Hefei23009 China The Key Laboratory of Process Optimization and Intelligent Decision-Making Ministry of Education China The National Engineering Laboratory for Big Data Distribution and Exchange Technologies Shanghai200135 China The West China Hospital of Sichuan University Sichuan Chengdu610041 China

Early detection of anxiety is crucial for reducing the suffering of individuals with mental disorders and improving treatment outcomes. Utilizing an mHealth platform for anxiety screening can be particularly practical in improving screening efficiency and reducing costs. However, the effectiveness of existing methods has been hindered by differences in mobile devices used to capture subjects' physical and mental evaluations, as well as by the variability in data quality and small sample size problems encountered in real-world settings. To address these issues, we propose a framework with spatiotemporal feature fusion for detecting anxiety nonintrusively. We use a feature extraction network based on a 3D convolutional network and long short-term memory ("3DCNN+LSTM") to fuse the spatiotemporal features of facial behavior and noncontact physiology, which reduces the impact of uneven data quality. Additionally, we design a similarity assessment strategy to address the issue of deteriorating model accuracy due to small sample sizes. Our framework is validated with a crew dataset from the real world and two public datasets: the University of Burgundy Franche-Comté Psychophysiological (UBFC-Phys) dataset and the Smart Reasoning for Well-being at Home and at Work for Knowledge Work (SWELL-KW) dataset. The experimental results indicate that our framework outperforms the comparison methods. © 2022, CC BY-NC-SA.

关键词： mHealth

Dynamic Viscosity of the ABC-stacked Multilayer Graphene in the Collisionless Regime

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Weiwei Shen, Yedi Zhan, Tianle Zhu, W. Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province College of Science China Jiliang University Hangzhou310018 China School of Science Westlake University 18 Shilongshan Road Hangzhou310024 China Hefei National Laboratory for Physical Sciences at the Microscale and Synergetic Innovation Center of Quantum Information and Quantum Physics University of Science and Technology of China Anhui Hefei230026 China Institute of Natural Sciences Westlake Institute for Advanced Study 18 Shilongshan Road Hangzhou310024 China

We explore the dynamic shear viscosity of the undoped ABC-stacked multilayer graphene based on the chiral-N effective Hamiltonian, where the chirality N is equivalent to the layer number. We investigate the dependence of the dynamic shear viscosity on the frequency in the collisionless regime and calculate Coulomb interaction corrections by three leading order Feynman diagrams: self-energy diagram, vertex diagram, and honey diagram. We propose that the dynamic shear viscosity is generated by the relaxation of momentum flux polarization through electron-hole excitations, and that the interaction can amplify this effect. Furthermore, our research indicates that the dynamic shear viscosity exhibits a robust linear positive dependence on N. This finding suggests that by making modifications to the number of layers in graphene, it is possible to finely tune the electron viscous effects. © 2024, CC0.

关键词： Graphene

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition