检索结果-内蒙古大学图书馆

NDD: A 3D Point Cloud Descriptor Based on Normal Distribution for Loop Closure Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Ruihao He, Li Zhang, Hong Lin, Xubin Guan, Yisheng The Department of Electromechanical Engineering Guangdong University of Technology China The Department of Electronic and Electrical Engineering Southern University of Science and Technology China Shenzhen Key Laboratory of Robotics and Computer Vision China

Loop closure detection is a key technology for long-term robot navigation in complex environments. In this paper, we present a global descriptor, named Normal Distribution Descriptor (NDD), for 3D point cloud loop closure detection. The descriptor encodes both the probability density score and entropy of a point cloud as the descriptor. We also propose a fast rotation alignment process and use correlation coefficient as the similarity between descriptors. Experimental results show that our approach outperforms the state-of-the-art point cloud descriptors in both accuracy and efficency. The source code is available and can be integrated into existing LiDAR odometry and mapping (LOAM) systems. © 2022, CC BY.

关键词： Normal distribution

WaveCNet: Wavelet integrated CNNs to suppress aliasing effect for noise-robust image classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Qiufu Shen, Linlin Guo, Sheng Lai, Zhihui Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China MyBank Ant Group Hangzhou310012 China

Though widely used in image classification, convolutional neural networks (CNNs) are prone to noise interruptions, i.e. the CNN output can be drastically changed by small image noise. To improve the noise robustness, we try to integrate CNNs with wavelet by replacing the common down-sampling (maxpooling, strided-convolution, and average pooling) with discrete wavelet transform (DWT). We firstly propose general DWT and inverse DWT (IDWT) layers applicable to various orthogonal and biorthogonal discrete wavelets like Haar, Daubechies, and Cohen, etc., and then design wavelet integrated CNNs (WaveCNets) by integrating DWT into the commonly used CNNs (VGG, ResNets, and DenseNet). During the down-sampling, WaveCNets apply DWT to decompose the feature maps into the low-frequency and high-frequency components. Containing the main information including the basic object structures, the low-frequency component is transmitted into the following layers to generate robust high-level features. The high-frequency components are dropped to remove most of the data noises. The experimental results show that WaveCNets achieve higher accuracy on ImageNet than various vanilla CNNs. We have also tested the performance of WaveCNets on the noisy version of ImageNet, ImageNet-C and six adversarial attacks, the results suggest that the proposed DWT/IDWT layers could provide better noise-robustness and adversarial robustness. When applying WaveCNets as backbones, the performance of object detectors (i.e., faster R-CNN and RetinaNet) on COCO detection dataset are consistently improved. We believe that suppression of aliasing effect, i.e. separation of low frequency and high frequency information, is the main advantages of our approach. The code of our DWT/IDWT layer and differentWaveCNets are available at https://***/CVISZU/ WaveCNet. © 2021, CC BY.

关键词： Signal sampling

Deep Learning-Enabled ISAC-OTFS Pre-equalization Design for Aerial-Terrestrial Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Weihao Guo, Jing Wang, Siqiang Wang, Xinyi Yuan, Weijie Fei, Zesong the School of Information and Electronics Beijing Institute of Technology Beijing100081 China the School of System Design and Intelligent Manufacturing The Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China

Orthogonal time frequency space (OTFS) modulation has been viewed as a promising technique for integrated sensing and communication (ISAC) systems and aerial-terrestrial networks, due to its delay-Doppler domain transmission property and strong Doppler-resistance capability. However, it also suffers from high processing complexity at the receiver. In this work, we propose a novel pre-equalization based ISAC-OTFS transmission framework, where the terrestrial base station (BS) executes pre-equalization based on its estimated channel state information (CSI). In particular, the mean square error of OTFS symbol demodulation and Cramér-Rao lower bound of sensing parameter estimation are derived, and their weighted sum is utilized as the metric for optimizing the pre-equalization matrix. To address the formulated problem while taking the time-varying CSI into consideration, a deep learning enabled channel prediction-based pre-equalization framework is proposed, where a parameter-level channel prediction module is utilized to decouple OTFS channel parameters, and a low-dimensional prediction network is leveraged to correct outdated CSI. A CSI processing module is then used to initialize the input of the pre-equalization module. Finally, a residual-structured deep neural network is cascaded to execute pre-equalization. Simulation results show that under the proposed framework, the demodulation complexity at the receiver as well as the pilot overhead for channel estimation, are significantly reduced, while the symbol detection performance approaches those of conventional minimum mean square error equalization and perfect CSI. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel estimation

UNIFORMER: UNIFIED TRANSFORMER FOR EFFICIENT SPATIOTEMPORAL REPRESENTATION LEARNING 10

学校读者我要写书评

暂无评论

UNIFORMER: UNIFIED TRANSFORMER FOR EFFICIENT SPATIOTEMPORAL ...

10th International Conference on Learning Representations, ICLR 2022

作者： Li, Kunchang Wang, Yali Gao, Peng Song, Guanglu Liu, Yu Li, Hongsheng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory Shanghai China SenseTime Research The Chinese University of Hong Kong Hong Kong

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been mainly driven by 3D convolutional neural networks and vision transformers. Although 3D convolution can efficiently aggregate local context to suppress local redundancy from a small 3D neighborhood, it lacks the capability to capture global dependency because of the limited receptive field. Alternatively, vision transformers can effectively capture long-range dependency by self-attention mechanism, while having the limitation on reducing local redundancy with blind similarity comparison among all the tokens in each layer. Based on these observations, we propose a novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy. Different from traditional transformers, our relation aggregator can tackle both spatiotemporal redundancy and dependency, by learning local and global token affinity respectively in shallow and deep layers. We conduct extensive experiments on the popular video benchmarks, e.g., Kinetics-400, Kinetics-600, and Something-Something V1&V2. With only ImageNet-1K pretraining, our UniFormer achieves 82.9%/84.8% top-1 accuracy on Kinetics-400/Kinetics-600, while requiring 10× fewer GFLOPs than other state-of-the-art methods. For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60.9% and 71.2% top-1 accuracy respectively. Code is available at https://***/Sense-X/UniFormer. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Redundancy

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

Fast Candidate Region Extraction for SAR Ship Target 37

学校读者我要写书评

暂无评论

Fast Candidate Region Extraction for SAR Ship Target

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Zhang, Panpan Luo, Haibo Xu, Zheng He, Miao Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Opto-Electronic Information Processing Shenyang110016 China The Key Lab of Image Understanding and Computer Vision Shenyang110016 China

ISBN: (纸本)9781665465366

At present, deep learning technology is widely used in ship target detection in synthetic aperture radar (SAR) images. However, high-resolution remote sensing SAR images cover a larger area and have larger image sizes. To be able to use the deep learning model for training and testing, the image needs to be cropped to the appropriate size. In a high-resolution SAR ship image, the ship target usually takes only a small part of the whole image. As a result, only part of the cropped image contains the target, and most of the rest are background regions. This will cause a lot of computational redundancy in the model inference stage. To solve this problem, a fast candidate region extraction algorithm is proposed in this paper for ship target extraction. The algorithm consists of three parts: firstly, extract the saliency map of the SAR ship image, secondly, perform median filtering on the segmented image, and thirdly, extract candidate regions. The superiority of the algorithm was demonstrated by experiments on the AIR-SARShip-1.0 dataset. © 2022 IEEE.

关键词： Synthetic aperture radar

Evading Detection Actively: Toward Anti-Forensics against Forgery Localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhuo, Long Luo, Shenghai Tan, Shunquan Chen, Han Li, Bin Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen Institute of Artificial Intelligence and Robotics for Society China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Anti-forensics seeks to eliminate or conceal traces of tampering artifacts. Typically, anti-forensic methods are designed to deceive binary detectors and persuade them to misjudge the authenticity of an image. However, to the best of our knowledge, no attempts have been made to deceive forgery detectors at the pixel level and mis-locate forged regions. Traditional adversarial attack methods cannot be directly used against forgery localization due to the following defects: 1) they tend to just naively induce the target forensic models to flip their pixel-level pristine or forged decisions;2) their anti-forensics performance tends to be severely degraded when faced with the unseen forensic models;3) they lose validity once the target forensic models are retrained with the anti-forensics images generated by them. To tackle the three defects, we propose SEAR (Self-supErvised Anti-foRensics), a novel self-supervised and adversarial training algorithm that effectively trains deep-learning anti-forensic models against forgery localization. SEAR sets a pretext task to reconstruct perturbation for self-supervised learning. In adversarial training, SEAR employs a forgery localization model as a supervisor to explore tampering features and constructs a deep-learning concealer to erase corresponding traces. We have conducted large-scale experiments across diverse datasets. The experimental results demonstrate that, through the combination of self-supervised learning and adversarial learning, SEAR successfully deceives the state-of-the-art forgery localization methods, as well as tackle the three defects regarding traditional adversarial attack methods mentioned above. Copyright © 2023, The Authors. All rights reserved.

关键词： Defects

Deep Learning and Network Analysis:Classifying and Visualizing Geologic Hazard Reports

学校读者我要写书评

暂无评论

Journal of Earth Science 2024年第4期35卷 1289-1303页

作者： Wenjia Li Liang Wu Xinde Xu Zhong Xie Qinjun Qiu Hao Liu Zhen Huang Jianguo Chen School of Geography and Information Engineering China University of GeosciencesWuhan430078China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of GeosciencesWuhan430078China School of Computer Science China University of GeosciencesWuhan430078China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural ResourcesShenzhen518034China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China Wuhan Geomatics Institute Wuhan430074China Faculty of Earth Resources China University of GeosciencesWuhan430074China

If progress is to be made toward improving geohazard management and emergency decision-making,then lessons need to be learned from past geohazard information.A geologic hazard report provides a useful and reliable source of information about the occurrence of an event,along with detailed information about the condition or factors of the *** such reports,however,can be a challenging process because these texts are often presented in unstructured long text formats,and contain rich specialized and detailed *** text classification is commonly used to mine disaster text data in open domains(e.g.,news and microblogs).But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse *** deficiencies are most obviously exposed in long text ***,this paper uses the bidirectional encoder representations from Transformers(BERT),to model long ***,utilizing a softmax layer to automatically extract text features and classify geohazards without manual *** latent Dirichlet allocation(LDA)model is used to examine the interdependencies that exist between causal variables to visualize *** proposed method is useful in enabling the machine-assisted interpretation of text-based ***,it can help users visualize causes,processes,and other geohazards and assist decision-makers in emergency responses.

关键词： geologic hazard network analysis latent dirichlet allocation text classification deep learning

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lai, Song Zhao, Zhe Zhu, Fei Lin, Xi Zhang, Qingfu Meng, Gaofeng Department of Computer Science City University of Hong Kong Hong Kong Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China City University of Hong Kong Shenzhen Research Institute Hong Kong University of Science and Technology of China China

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience replay methods, which store and replay past data alongside new data, have become a widely adopted approach to mitigate catastrophic forgetting. However, these methods neglect the dynamic nature of the stability-plasticity trade-off and aim to find a fixed and unchanging balance, resulting in suboptimal adaptation during training and inference. In this paper, we propose Pareto Continual Learning (ParetoCL), a novel framework that reformulates the stability-plasticity trade-off in continual learning as a multi-objective optimization (MOO) problem. ParetoCL introduces a preference-conditioned model to efficiently learn a set of Pareto optimal solutions representing different trade-offs and enables dynamic adaptation during inference. From a generalization perspective, ParetoCL can be seen as an objective augmentation approach that learns from different objective combinations of stability and plasticity. Extensive experiments across multiple datasets and settings demonstrate that ParetoCL outperforms state-of-the-art methods and adapts to diverse continual learning scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning