检索结果-内蒙古大学图书馆

Learning to Learn Transferable Generative Attack for Person Re-Identification

学校读者我要写书评

暂无评论

IEEE Transactions on Image Processing 2025年 PP卷 PP页

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based crossmodel&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. © 1992-2012 IEEE.

关键词： Generative adversarial networks

An insulator feature-enhanced segmentation method based on the residual-type attention mechanism

学校读者我要写书评

暂无评论

An insulator feature-enhanced segmentation method based on t...

IEEE Advanced Information Management,Communicates,Electronic and Automation control Conference (IMCEC)

作者： Xin Tang Jianxu Mao Junfei Yi Ziming Tao Zhenyu He College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Vision Perception and Control Technology Changsha China

ISBN: (纸本)9781665479691

As an crucial component of power line, the timely check for the state of insulator is necessary for the normal running of transmission lines. In view of debasement of insulator segmentation accuracy in current transmission line caused by complex background, low contrast, and the quality of images is not guaranteed, we improve U-Net by combining attention mechanism and residual connection. Residual connection is added to the encoder part to improve the extraction of low-level semantic information, and the attention mechanism is added to the decoder part for integrating high and low level features better and reduce the error between them. We confirm the effectiveness of the improved module through experiments, while the results showing that the improved U-Net model segmentation performance on insulator dataset is improved from 0.875 to 0.912. And our method also outperforms previous segmentation work on insulator dataset.

关键词： Image segmentation Power transmission lines Automation Semantics Insulators Feature extraction Information management

Power Grid Fastener Defect Detection Based on Dual Context Information Fusion

学校读者我要写书评

暂无评论

Power Grid Fastener Defect Detection Based on Dual Context I...

IEEE Advanced Information Management,Communicates,Electronic and Automation control Conference (IMCEC)

作者： Liu Qingxian Mao Jianxu Yi Junfei Tao Ziming Yu Junlong College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Vision Perception and Control Technology Changsha China

ISBN: (纸本)9781665479691

The working state of fasteners is closely related to the safe and stable operation of the power grid. However, the performance of the existing fastener defect detection models is not enough to meet the requirements, because the size of object is small, the environment is complex, the sample size is unbalanced and so on. Therefore, we design a simple but effective feature fusion method, called Double Context Information Enhancement Module. The model can fully learn the features of fasteners by expanding the receptive field of the feature map during the construction of the feature pyramid, and the feature expression ability of fasteners can be enhanced by learning the features of adjacent layers after the construction of the feature pyramid. Through experiments, we proved that DCEM can improve about 8.8AP compared with the original model, and at the same time, the effectiveness and advancement of DCEM are proved by comparing with SOTA.

关键词： Correlation Automation Aggregates Fasteners Feature extraction Power grids Information management

A Flexible Framework for Universal Computational Aberration Correction via Automatic Lens Library Generation and Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Qi Gao, Yao Gao, Shaohua Yi, Zhonghua Sun, Lei Shi, Hao Yang, Kailun Wang, Kaiwei Bai, Jian State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou310027 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China

Emerging universal Computational Aberration Correction (CAC) paradigms provide an inspiring solution to light-weight and high-quality imaging without repeated data preparation and model training to accommodate new lens designs. However, the training databases in these approaches, i.e., the lens libraries (LensLibs), suffer from their limited coverage of real-world aberration behaviors. Moreover, it is challenging to train a universal model for reliable results in a zero-shot manner, whose inflexible tuning pipeline is also confined to the lens-descriptions-known case. In this work, we set up an OmniLens framework for universal CAC, considering both the generalization ability and flexibility. OmniLens extends the idea of universal CAC to a broader concept, where a base model is trained as the pre-trained model for three cases, including zero-shot CAC with the pre-trained model, few-shot CAC with a little lens-specific data for fine-tuning, and domain adaptive CAC using domain adaptation for lens-descriptions-unknown lens. In terms of OmniLens’s data foundation, we first propose an Evolution-based Automatic Optical Design (EAOD) pipeline to construct the LensLib automatically, coined AODLib, whose diversity is enriched by an evolution framework, with comprehensive constraints and a hybrid optimization strategy for achieving realistic aberration behaviors. For network design, we introduce the guidance of high-quality codebook priors to facilitate both zero-shot CAC and few-shot CAC, which enhances the model’s generalization ability, while also boosting its convergence in a few-shot case. Furthermore, based on the statistical observation of dark channel priors in optical degradation, we design an unsupervised regularization term to adapt the base model to the target descriptions-unknown lens using its aberration images without ground truth. We validate the proposed OmniLens framework on 4 manually designed low-end lenses with various structures and aberration behaviors.

关键词： Aberrations

Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Yizhou Yang, Fan Zhu, Guoliang Li, Gen Shi, Hao Zuo, Yukun Chen, Wenrui Li, Zhiyong Yang, Kailun School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China School of Informatics University of Edinburgh United Kingdom State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China

Affordance refers to the functional properties that an agent perceives and utilizes from its environment, and is key perceptual information required for robots to perform actions. This information is rich and multimodal in nature. Existing multimodal affordance methods face limitations in extracting useful information, mainly due to simple structural designs, basic fusion methods, and large model parameters, making it difficult to meet the performance requirements for practical deployment. To address these issues, this paper proposes the BiT-Align image-depth-text affordance mapping framework. The framework includes a Bypass Prompt Module (BPM) and a Text Feature Guidance (TFG) attention selection mechanism. BPM integrates the auxiliary modality depth image directly as a prompt to the primary modality RGB image, embedding it into the primary modality encoder without introducing additional encoders. This reduces the model’s parameter count and effectively improves functional region localization accuracy. The TFG mechanism guides the selection and enhancement of attention heads in the image encoder using textual features, improving the understanding of affordance characteristics. Experimental results demonstrate that the proposed method achieves significant performance improvements on public AGD20K and HICO-IIF datasets. On the AGD20K dataset, compared with the current state-of-the-art method, we achieve a 6.0% improvement in the KLD metric, while reducing model parameters by 88.8%, demonstrating practical application values. The source code will be made publicly available at https://***/DAWDSE/BiT-Align. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

LanCOPE: Language-Guided Category-Level Object Pose Estimation from a Single RGB Image

学校读者我要写书评

暂无评论

IEEE robotics and Automation Letters 2025年第7期10卷 7555-7562页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Dai, Zhenqi Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha 410082 China Central South University School of Architecture and Art Changsha 410082 China The University of Western Australia Department of Computer Science and Software Engineering 6009 WA Australia

Monocular RGB-based category-level object pose estimation is more practical and cost-effective for robotics. However, existing methods do not fully exploit the rich semantic and contextual information in multimodal data (e.g. language) that provides additional object attributes to guide the model in extracting category features more reliably. We propose a language-guided category-level object pose estimation method (LanCOPE), taking a single RGB image as input. Our method uses DINOv2 to recover depth from a single RGB image and converts it into point cloud to perceive the object's geometry. We then introduce language descriptions for the RGB image, estimated point cloud and overall scene to better guide the point cloud encoder and image encoder in learning category features. We develop a cross-modal differential perception feature fusion network to fuse multimodal features. This network employs a differential perception module to eliminate redundant information across different modalities, highlighting signifcant semantic differences and similarities. Furthermore, it uses a cross-attention mechanism to fuse the semantic information of the language and vision features, improving the overall perception. Finally, we design a denoising network based on the skip fusion transformer to recover the object pose accurately. Extensive experiments on REAL275 and Wild6D datasets show that LanCOPE achieves state-of-the-art performance. Our code is available at LanCOPE. © 2016 IEEE.

关键词： category-level object pose estimation languag RGB image

L₁ Adaptive control-Based Formation Tracking of Multiple Quadrotors Without Linear Velocity Feedback Under Unknown Disturbances

学校读者我要写书评

暂无评论

IEEE Transactions on Automation Science and engineering 2024年 22卷 5804-5815页

作者： Yang Hu Zhiqiang Miao Yaonan Wang Haoming Tang Xiangke Wang Wei He College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Visual Perception and Control Changsha China College of Intelligence Science and Technology National University of Defense Technology Changsha China School of Intelligence Science and Technology and the Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education University of Science and Technology Beijing Beijing China

This paper addresses the problem of formation control for a quadrotor swarm (QS) system with directed graph topology under external environmental disturbances and unreliable internal state acquisition. The proposed distributed robust control framework, based on a gemetric controller, incorporates ${\mathcal {L}}_control$ adaptive controllers and differentiator systems. First, the geometric formation controller is designed to implement the formation control of the nominal system. Then, ${\mathcal {L}}_control$ adaptive controllers are designed separately for each quadrotor’s position loop and attitude loop subsystems to address the effects of uncertainties such as external time-varying disturbances (matched and unmatched disturbances) and different mass variations of quadrotors. Furthermore, the differentiator system is devised to accurately estimate the higher-order derivatives of the non-directly-measurable velocity information and the virtual translation control signal, which enhances system accuracy while reducing computational complexity. The Lyapunov stability theory is employed to analyze the stability of the closed-loop system. Finally, the effectiveness and exceptional performance of this approach in QS formation control were validated through numerical simulation and experimental results. Note to Practitioners—The inspiration for this article comes from the issue of formation control in a cluster of quadrotor drones, which is also applicable to formation control in other types of drones. In this paper, a formation control algorithm based on ${\mathcal {L}}_control$ adaptive control strategy and arbitrary-order differentiation is designed. This algorithm can address not only the issue of time-varying wind disturbances frequently encountered during quadrotor drone flights but also the effects of unpredictable velocities and inconsistent masses of quadrotor drones. The disturbance rejection capability of this scheme enables quadrotor drones to be applied more safely and r

关键词： Quadrotors Formation control Adaptive control Topology Drones Autonomous aerial vehicles Uncertainty

SF-TIM: A Simple Framework for Enhancing Quadrupedal robot Jumping Agility by Combining Terrain Imagination and Measurement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Ze Li, Yang Xu, Long Shi, Hao Ma, Zunwang Chu, Zhen Li, Chao Gao, Fei Yang, Kailun Wang, Kaiwei State Key Laboratory of Modern Optical Instrumentation Zhejiang University China School of Robotics and National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China State Key Laboratory of Industrial Control Technology Zhejiang University China DeepRobotics Co. Ltd. China

Dynamic jumping on high platforms and over gaps differentiates legged robots from wheeled counterparts. Compared to walking on rough terrains, dynamic locomotion on abrupt surfaces requires fusing proprioceptive and exteroceptive perception for explosive movements. In this paper, we propose SF-TIM (Simple Framework combining Terrain Imagination and Measurement), a single-policy method that enhances quadrupedal robot jumping agility, while preserving their fundamental blind walking capabilities. In addition, we introduce a terrain-guided reward design specifically to assist quadrupedal robots in high jumping, improving their performance in this task. To narrow the simulation-to-reality gap in quadrupedal robot learning, we introduce a stable and high-speed elevation map generation framework, enabling zero-shot simulation-to-reality transfer of locomotion ability. Our algorithm has been deployed and validated on both the small-/large-size quadrupedal robots, demonstrating its effectiveness in real-world applications: the robot has successfully traversed various high platforms and gaps, showing the robustness of our proposed approach. A demo video has been made available at https://***/SF-TIM. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Qi Gao, Shaohua Gao, Yao Yang, Kailun Yi, Zhonghua Shi, Hao Sun, Lei Wang, Kaiwei The State Key Laboratory of Modern Optical Instrumentation The National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China

High-quality panoramic images with a Field of View (FoV) of 360° are essential for contemporary panoramic computer vision tasks. However, conventional imaging systems come with sophisticated lens designs and heavy optical components. This disqualifies their usage in many mobile and wearable applications where thin and portable, minimalist imaging systems are desired. In this paper, we propose a Panoramic Computational Imaging Engine (PCIE) to achieve minimalist and high-quality panoramic imaging. With less than three spherical lenses, a Minimalist Panoramic Imaging Prototype (MPIP) is constructed based on the design of the Panoramic Annular Lens (PAL), but with low-quality imaging results due to aberrations and small image plane size. We propose two pipelines, i.e. Aberration Correction (AC) and Super-Resolution and Aberration Correction (SR&AC), to solve the image quality problems of MPIP, with imaging sensors of small and large pixel size, respectively. To leverage the prior information of the optical system, we propose a Point Spread Function (PSF) representation method to produce a PSF map as an additional modality. A PSF-aware Aberration-image Recovery Transformer (PART) is designed as a universal network for the two pipelines, in which the self-attention calculation and feature extraction are guided by the PSF map. We train PART on synthetic image pairs from simulation and put forward the PALHQ dataset to fill the gap of real-world high-quality PAL images for low-level vision. A comprehensive variety of experiments on synthetic and real-world benchmarks demonstrates the impressive imaging results of PCIE and the effectiveness of the PSF representation. We further deliver heuristic experimental findings for minimalist and high-quality panoramic imaging, in terms of the choices of prototype and pipeline, network architecture, training strategies, and dataset construction. Our dataset and code will be available at https://***/zju-jiangqi/PCIE-PART. Copyrig

关键词： Optical transfer function