检索结果-内蒙古大学图书馆

Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Nguyen, Cuong Do, Thanh-Toan Carneiro, Gustavo School of Computer Science University of Adelaide Australia Department of Data Science and AI Monash University Australia Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

Learning from noisy labels (LNL) plays a crucial role in deep learning. The most promising LNL methods rely on identifying clean-label samples from a dataset with noisy annotations. Such an identification is challenging because the conventional LNL problem, which assumes a single noisy label per instance, is non-identifiable, i.e., clean labels cannot be estimated theoretically without additional heuristics. In this paper, we aim to formally investigate this identifiability issue using multinomial mixture models to determine the constraints that make the problem identifiable. Specifically, we discover that the LNL problem becomes identifiable if there are at least 2C − 1 noisy labels per instance, where C is the number of classes. To meet this requirement without relying on additional 2C − 2 manual annotations per instance, we propose a method that automatically generates additional noisy labels by estimating the noisy label distribution based on nearest neighbours. These additional noisy labels enable us to apply the Expectation-Maximisation algorithm to estimate the posterior probabilities of clean labels, which are then used to train the model of interest. We empirically demonstrate that our proposed method is capable of estimating clean labels without any heuristics in several label noise benchmarks, including synthetic, web-controlled, and real-world label noises. Furthermore, our method performs competitively with many state-of-the-art methods. © 2023, CC BY.

关键词： Deep learning

Task Weighting in Meta-learning with Trajectory Optimisation

学校读者我要写书评

暂无评论

arXiv 2023年

Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions. In this paper, we introduce a new principled and fully-automated task-weighting algorithm for meta-learning methods. By considering the weights of tasks within the same mini-batch as an action, and the meta-parameter of interest as the system state, we cast the task-weighting meta-learning problem to a trajectory optimisation and employ the iterative linear quadratic regulator to determine the optimal action or weights of tasks. We theoretically show that the proposed algorithm converges to an ∊0-stationary point, and empirically demonstrate that the proposed approach out-performs common hand-engineering weighting methods in two few-shot learning benchmarks. © 2023, CC BY.

关键词： Learning algorithms

RSZero-CSAT: Zero-Shot Scene Classification in Remote Sensing Imagery using a Cross Semantic Attribute-guided Transformer

学校读者我要写书评

暂无评论

RSZero-CSAT: Zero-Shot Scene Classification in Remote Sensin...

International Joint Conference on Neural Networks (IJCNN)

作者： Damalla Rambabu Swetha G Rajeshreddy Datla Vishnu Chalavadi C Krishna Mohan Department of Computer Science and Engineering Indian Institute of Technology Hyderabad Dept. of Space Advanced Data Processing Research Institute (ADRIN) Secunderabad India Indian Institute of Technology Tirupati India

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Zero-shot learning (ZSL) based scene classification aims to recognize unseen classes by transferring semantic information from seen classes. The applicability of ZSL for scene classification in remote sensing images becomes challenging due to the complexity of scenes. Earlier attention-based methods are ineffective for extracting discriminative region-based features within a single image. This limitation hinders their ability to achieve transferability and accurately localize object attributes, which is essential for extracting discriminative region-based features. Hence, we propose a method for zero-shot scene classification in remote sensing images using a cross-semantic attribute-guided Transformer named RSZero-CSAT. Firstly, the semantic information is acquired using shared remote sensing semantic attributes to localize object attributes that characterize discriminative region features. Then, a Transformer in RSZero-CSAT is employed to localize object attributes within visual features accurately, enhancing the effectiveness of semantic information transfer in ZSL. Specifically, the RSZero-CSAT employs a semantic attribute → visual Transformer (SAVT) and a visual → semantic attribute Transformer (VSAT) components to extract visual features guided by semantic attributes and semantic attribute features guided by visual features, respectively. Further, SAVT and VSAT mutually learn and collaborate to obtain semantically enriched visual representations, leveraging prediction-level and feature-level semantic collaborative losses for capturing crucial semantic information. Finally, the semantically enriched visual representations obtained from SAVT and VSAT are combined to facilitate visual-semantic interactions in collaboration with class semantic vectors to classify ZSL. Our experimental results demonstrate the impact of RSZero-CSAT in improving the performance of unseen classes on four scene classification benchmark datasets in remote sensing images. The code is avai

关键词： Visualization Scene classification Zero-shot learning Semantics Collaboration Benchmark testing Feature extraction

Look Closer to Your Enemy: Learning to Attack via Teacher-Student Mimicking

学校读者我要写书评

暂无评论

IEEE Transactions on Big data 2025年

作者： Wang, Mingjie Guo, Jianxiong Li, Sirui Xiao, Dingwen Tang, Zhiqing Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China

Deep neural networks have significantly advanced person re-identification (ReID) applications in the realm of the industrial internet, yet they remain vulnerable. Thus, it is crucial to study the robustness of ReID systems, as there are risks of adversaries using these vulnerabilities to compromise industrial surveillance systems. Current adversarial methods focus on generating attack samples using misclassification feedback from victim models (VMs), neglecting VM's cognitive processes. We seek to address this by producing authentic ReID attack instances through VM cognition decryption. This approach boasts advantages like better transferability to open-set ReID tests, easier VM misdirection, and enhanced creation of realistic and undetectable assault images. However, the task of deciphering the cognitive mechanism in VM is widely considered to be a formidable challenge. In this paper, we propose a novel inconspicuous and controllable ReID attack baseline, LCYE (Look Closer to Your Enemy), to generate adversarial query images. Specifically, LCYE first distills VM's knowledge via teacher-student memory mimicking the proxy task. This knowledge prior serves as an unambiguous cryptographic token, encapsulating elements deemed indispensable and plausible by the VM, with the intent of facilitating precise adversarial misdirection. Further, benefiting from the multiple opposing task framework of LCYE, we investigate the interpretability and generalization of ReID models from the view of the adversarial attack, including cross-domain adaption, cross-model consensus, and online learning process. Extensive experiments on four ReID benchmarks show that our method outperforms other state-of-the-art attackers with a large margin in white-box, black-box, and target attacks. The source code can be found at https://***/MingjieWang0606/LCYE-attack_reid. © 2015 IEEE.

关键词： Adversarial machine learning

BLESSEMFLOOD21: ADVANCING FLOOD ANALYSIS WITH A HIGH-RESOLUTION GEOREFERENCED dataSET FOR HUMANITARIAN AID SUPPORT

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Polushko, Vladyslav Jenal, Alexander Bongartz, Jens Weber, Immanuel Hatic, Damjan Rösch, Ronald März, Thomas Rauhut, Markus Weinmann, Andreas Image Processing Department Fraunhofer ITWM Kaiserslautern Germany Working Group Algorithms for Computer Vision Imaging and Data Analysis Hochschule Darmstadt Darmstadt Germany Center for Machine Learning and Sensor Technology Hochschule Koblenz Remagen Germany

关键词： Floods

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

Automatic Detection and Characterization of Human Veins Using Infra-Red Image processing

学校读者我要写书评

暂无评论

Journal of computer and Communications 2024年第9期12卷 141-159页

作者： Jean Ndoumbe Brice Ekobo Akoa Gaelle Patricia Talotsing Frederic Franck Kounga Samuel Kaissassou Bertin Chouanmo Njo Laboratory of Computer Engineering Data Science and Artificial Intelligence Department of Computer & Telecommunications Engineering National Higher Polytechnic School Douala Cameroon Laboratory of Electrical Engineering Mechatronics and Signal Processing Department of Electrical & Telecommunications Engineering National Advanced School of Engineering Yaound Cameroon Mobile Computing and Networking Research Laboratory Department of Computer and Software Engineering Polytechnique Montreal Montreal Canada DigiPlus SARL Bonamoussadi Douala Cameroon

The detection and characterization of human veins using infrared (IR) image processing have gained significant attention due to its potential applications in biometric identification, medical diagnostics, and vein-based authentication systems. This paper presents a low-cost approach for automatic detection and characterization of human veins from IR images. The proposed method uses image processing techniques including segmentation, feature extraction, and, pattern recognition algorithms. Initially, the IR images are preprocessed to enhance vein structures and reduce noise. Subsequently, a CLAHE algorithm is employed to extract vein regions based on their unique IR absorption properties. Features such as vein thickness, orientation, and branching patterns are extracted using mathematical morphology and directional filters. Finally, a classification framework is implemented to categorize veins and distinguish them from surrounding tissues or artifacts. A setup based on Raspberry Pi was used. Experimental results of IR images demonstrate the effectiveness and robustness of the proposed approach in accurately detecting and characterizing human. The developed system shows promising for integration into applications requiring reliable and secure identification based on vein patterns. Our work provides an effective and low-cost solution for nursing staff in low and middle-income countries to perform a safe and accurate venipuncture.

关键词： Vein Detection Blood Radiation Infrared Image CLAHE Algorithm Raspberry Pi

Energy Efficiency Maximization in RISs-Assisted UAVs-Based Edge Computing Network Using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

Big data Mining and Analytics 2024年第4期7卷 1065-1083页

作者： Chuanwen Luo Jian Zhang Jianxiong Guo Yi Hong Zhibo Chen Shuyang Gu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083Chinaand also with the Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland AdministrationBeijing 100083China Advanced Institute of Natural Sciences Beijing Normal UniversityZhuhai 519087Chinaand also with the Guangdong Key Lab of AI and Multi-Modal Data ProcessingBNU-HKBU United International CollegeZhuhai 519087China Department of Computer Information Systems Texas A&M University-Central TexasKilleenTX 76549USA

Edge Computing(EC)pushes computational capability to the Terrestrial Devices(TDs),providing more efficient and faster computing *** Aerial Vehicles(UAVs)equipped with EC servers can be flexibly deployed,even in complex terrains,to provide mobile computing services at all ***,UAVs can establish an air-to-ground line-of-sight link with TDs to improve the quality of communication ***,the UAV-to-TD link may be obstructed by ground obstacles such as buildings or trees,leading to sub-optimal data transmission *** surmount this issue,Reconfigurable Intelligent Surfaces(RISs)emerge as a promising technology capable of intelligently reflecting signals to enhance communication quality between UAVs and *** this paper,we consider the RISs-assisted multi-UAVs collaborative edge Computing Network(RUCN)in urban environment,in which we study the computational offloading *** goal is to maximize the overall energy efficiency of UAVs by jointly optimizing the flight duration and trajectories of UAVs,and the phase shifts of *** is worth noting that this problem has been formally established as ***,we propose the Deep Deterministic Policy Gradients based UAV Trajectory and RIS Phase shift optimization algorithm(UTRP-DDPG)to solve this complex optimization *** results of extensive numerical experiments show that the proposed algorithm outperforms the other benchmark algorithms under various parameter ***,the UTRP-DDPG algorithm improves the UAV energy efficiency by at least 2%compared to DQN algorithm.

关键词： edge computing computing offloading Unmanned Aerial Vehicle(UAV) Reconfigurable Intelligent Surface(RIS) deep reinforcement learning