检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hui, Le Wang, Lingpeng Tang, Linghua Lan, Kaihao Xie, Jin Yang, Jian Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security PCA Lab School of Computer Science and Engineering Nanjing University of Science and Technology China

Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area. Due to the large appearance variation between the template and search area during tracking, how to learn the robust cross correlation between them for identifying the potential target in the search area is still a challenging problem. In this paper, we explicitly use Transformer to form a 3D Siamese Transformer network for learning robust cross correlation between the template and the search area of point clouds. Specifically, we develop a Siamese point Transformer network to learn shape context information of the target. Its encoder uses self-attention to capture non-local information of point clouds to characterize the shape information of the object, and the decoder utilizes cross-attention to upsample discriminative point features. After that, we develop an iterative coarse-to-fine correlation network to learn the robust cross correlation between the template and the search area. It formulates the cross-feature augmentation to associate the template with the potential target in the search area via cross attention. To further enhance the potential target, it employs the ego-feature augmentation that applies self-attention to the local k-NN graph of the feature space to aggregate target features. Experiments on the KITTI, nuScenes, and Waymo datasets show that our method achieves state-of-the-art performance on the 3D single object tracking task. Source code is available at https://***/fpthink/STNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Learning superpoint graph cut for 3D instance segmentation 22

Learning superpoint graph cut for 3D instance segmentation

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Le Hui Linghua Tang Yaqi Shen Jin Xie Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9781713871088

3D instance segmentation is a challenging task due to the complex local geometric structures of objects in point clouds. In this paper, we propose a learning-based superpoint graph cut method that explicitly learns the local geometric structures of the point cloud for 3D instance segmentation. Specifically, we first oversegment the raw point clouds into superpoints and construct the superpoint graph. Then, we propose an edge score prediction network to predict the edge scores of the superpoint graph, where the similarity vectors of two adjacent nodes learned through cross-graph attention in the coordinate and feature spaces are used for regressing edge scores. By forcing two adjacent nodes of the same instance to be close to the instance center in the coordinate and feature spaces, we formulate a geometry-aware edge loss to train the edge score prediction network. Finally, we develop a superpoint graph cut network that employs the learned edge scores and the predicted semantic classes of nodes to generate instances, where bilateral graph attention is proposed to extract discriminative features on both the coordinate and feature spaces for predicting semantic labels and scores of instances. Extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, show that our method achieves new state-of-the-art performance on 3D instance segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A single-loop accelerated extra-gradient difference algorithm with improved complexity bounds for constrained minimax optimization 23

A single-loop accelerated extra-gradient difference algorith...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yuanyuan Liu Fanhua Shang Weixin An Junhao Liu Hongying Liu Zhouchen Lin Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China School of Computer Science and Technology College of Intelligence and Computing Tianjin University Medical College Tianjin University China and Peng Cheng Laboratory National Key Lab of General AI School of Intelligence Science and Technology Peking University and Institute for Artificial Intelligence Peking University and Peng Cheng Laboratory

In this paper, we propose a novel extra-gradient difference acceleration algorithm for solving constrained nonconvex-nonconcave (NC-NC) minimax problems. In particular, we design a new extra-gradient difference step to obtain an important quasi-cocoercivity property, which plays a key role to significantly improve the convergence rate in the constrained NC-NC setting without additional structural assumption. Then momentum acceleration is also introduced into our dual accelerating update step. Moreover, we prove that, to find an ε-stationary point of the function f, the proposed algorithm attains the complexity O(ε-2) in the constrained NC-NC setting, while the best-known complexity bound is Õ(ε-4), where Õ(·) hides logarithmic factors compared to Õ(·). As the special cases of the constrained NC-NC setting, the proposed algorithm can also obtain the same complexity Õ(ε-2) for both the nonconvex-concave (NC-C) and convex-nonconcave (C-NC) cases, while the best-known complexity bounds are Õ(ε-2.5) for the NC-C case and Õ(ε-4) for the C-NC case. For fair comparison with existing algorithms, we also analyze the complexity bound to find ε-stationary point of the primal function ϕ for the constrained NC-C problem, which shows that our algorithm can improve the complexity bound from Õ(ε-3) to Õ(ε-2). To the best of our knowledge, this is the first time that the proposed algorithm improves the best-known complexity bounds from Õ(ε-4) and Õ(ε-3) to Õ(ε-2) in both the NC-NC and NC-C settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learned interpretable residual extragradient ISTA for sparse coding

arXiv

引用

arXiv 2021年

作者： Kong, Lin Sun, Wei Shang, Fanhua Liu, Yuanyuan Liu, Hongying Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China Peng Cheng Laboratory Shenzhen China

Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. In particular, our algorithm can also provide the interpretability for Res-Net to a certain extent. From a theoretical perspective, we prove that our method attains linear convergence. In practice, extensive empirical results verify the advantages of our method. © 2021, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Cold-Cathode X-ray Source Based intelligent Fault Detection for Drill Tools 8th

Cold-Cathode X-ray Source Based Intelligent Fault Detection ...

引用

8th International Field Exploration and Development Conference, IFEDC 2019

作者： Li, Jing Zhu, Bing Liu, Bo School of Electronic Engineering Xi’an Shiyou University Xi’an China Department Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Joint International Research Laboratory of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi’an China

ISBN: (纸本)9789811524844

The drill tools include drill pipe, drill collar and other joint tools, and their minor damage will lead to serious accidents such as jump drilling, collapse, sticking and so on. In order to ensure the safety and reduce the loss, it is very important to detect the drill tool. The conventional detection methods are manual visual inspection and ultrasonic based thread flaw detection. The disadvantages are low detection efficiency, low detection sensitivity and high miss detection rate. In this paper, a new intelligent fault detection technology based on the cold cathode X-ray is presented. Combined with the cold-cathode X-ray source of sealed tube and digital detector, an adaptive deep recognition algorithm is exploited for the micro-damage. This proposed method can improve the detection efficiently, ensure the quality of drill tools, and reduce the accident. It provides a foundation for the development of small and convenient equipment for fault detection. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation

arXiv

引用

arXiv 2023年

作者： Jiang, Haobo Salzmann, Mathieu Dang, Zheng Xie, Jin Yang, Jian PCA Lab Nanjing University of Science and Technology China CVLab EPFL Switzerland ClearSpace Switzerland PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which progressively refines the pose of the source point cloud to obtain a precise alignment with the model point cloud. Training our framework involves two operations: An SE(3) diffusion process and an SE(3) reverse process. The SE(3) diffusion process gradually perturbs the optimal rigid transformation of a pair of point clouds by continuously injecting noise (perturbation transformation). By contrast, the SE(3) reverse process focuses on learning a denoising network that refines the noisy transformation step-by-step, bringing it closer to the optimal transformation for accurate pose estimation. Unlike standard diffusion models used in linear Euclidean spaces, our diffusion model operates on the SE(3) manifold. This requires exploiting the linear Lie algebra se(3) associated with SE(3) to constrain the transformation transitions during the diffusion and reverse processes. Additionally, to effectively train our denoising network, we derive a registration-specific variational lower bound as the optimization objective for model learning. Furthermore, we show that our denoising network can be constructed with a surrogate registration model, making our approach applicable to different deep registration networks. Extensive experiments demonstrate that our diffusion registration framework presents outstanding pose estimation performance on the real-world TUD-L, LINEMOD, and Occluded-LINEMOD datasets. Code is available at https://***/JiangHB/DiffusionReg. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

arXiv

引用

arXiv 2022年

作者： Shen, Yaqi Hui, Le Jiang, Haobo Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Unsupervised point cloud registration algorithm usually suffers from the unsatisfied registration precision in the partially overlapping problem due to the lack of effective inlier evaluation. In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration. It is expected to capture the discriminative geometric difference between the source neighborhood and the corresponding pseudo target neighborhood for effective inlier distinction. Specifically, our model consists of a matching map refinement module and an inlier evaluation module. In our matching map refinement module, we improve the point-wise matching map estimation by integrating the matching scores of neighbors into it. The aggregated neighborhood information potentially facilitates the discriminative map construction so that high-quality correspondences can be provided for generating the pseudo target point cloud. Based on the observation that the outlier has the significant structure-wise difference between its source neighborhood and corresponding pseudo target neighborhood while this difference for inlier is small, the inlier evaluation module exploits this difference to score the inlier confidence for each estimated correspondence. In particular, we construct an effective graph representation for capturing this geometric difference between the neighborhoods. Finally, with the learned correspondences and the corresponding inlier confidence, we use the weighted SVD algorithm for transformation estimation. Under the unsupervised setting, we exploit the Huber function based global alignment loss, the local neighborhood consensus loss, and spatial consistency loss for model optimization. The experimental results on extensive datasets demonstrate that our unsupervised point cloud registration method can yield comparable performance. Our code is available at https://***/supersyq/RIENet. Copyright © 2022, The Authors. All rights

关键词： Surface measurement

来源：评论

学校读者我要写书评

暂无评论

Pick of the Bunch: Detecting Infrared Small Targets Beyond Hit-Miss Trade-Offs via Selective Rank-Aware Attention

arXiv

引用

arXiv 2024年

作者： Dai, Yimian Pan, Peiwen Qian, Yulei Li, Yuxuan Li, Xiang Yang, Jian Wang, Huan PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image Video Understanding for Social Security China The department of intelligence science School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Nanjing Marine Radar Institute Nanjing China VCIP CS Nankai University China The NKIARI Futian Shenzhen China

Infrared small target detection faces the inherent challenge of precisely localizing dim targets amidst complex background clutter. Traditional approaches struggle to balance detection precision and false alarm rates. To break this dilemma, we propose SeRankDet, a deep network that achieves high accuracy beyond the conventional hit-miss trade-off, by following the "Pick of the Bunch" principle. At its core lies our Selective Rank-Aware Attention (SeRank) module, employing a non-linear Top-K selection process that preserves the most salient responses, preventing target signal dilution while maintaining constant complexity. Furthermore, we replace the static concatenation typical in U-Net structures with our Large Selective Feature Fusion (LSFF) module, a dynamic fusion strategy that empowers SeRankDet with adaptive feature integration, enhancing its ability to discriminate true targets from false alarms. The network’s discernment is further refined by our Dilated Difference Convolution (DDC) module, which merges differential convolution aimed at amplifying subtle target characteristics with dilated convolution to expand the receptive field, thereby substantially improving target-background separation. Despite its lightweight architecture, the proposed SeRankDet sets new benchmarks in state-of-the-art performance across multiple public datasets. The code is available at https://***/GrokCV/SeRankDet. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An R-SIFT image Matching intelligent Algorithm Applied to Hardware Trojan Detection

An R-SIFT Image Matching Intelligent Algorithm Applied to Ha...

引用

作者： Chen Sun Pujiang Liang Lingling Li Jingjing Ma Licheng Jiao Fang Liu Science and Technology on Reliability Physics and Application of Electronic Component Laboratory Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and ComputationJoint International Research Laboratory of Intelligent Perception and ComputationSchool of Artificial IntelligenceXidian University

Malicious modification, deletion or addition of some modules in the integrated circuits(ICs) will cause the chip to be attacked, which is called Hardware Trojans(HTs). Reverse engineering(RE) is a classic destructive method and widely used in HTs detection. However, RE is very time-consuming and error prone. In this paper, based on RE, we propose the R-SIFT algorithm to match image and reformulate the Trojan detection problem as change detection problem. For the R-SIFT algorithm, the ratio of exponentially weighted averages(Roewa) operator is introduced into the scale-invariant feature transform(SIFT) algorithm. Experiments show that the proposed method has 7 to 56 times more matching points than the original SIFT can be effectively applied to HTs detection.

关键词： Trojan detection R-SIFT image matching

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

arXiv

引用

arXiv 2022年

作者： Bian, Yikai Hui, Le Qian, Jianjun Xie, Jin PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the knowledge from the source domain to the target domain, which may cause the semantic ambiguity of the feature space. In this paper, we propose a graph-based framework to explore the local-level feature alignment between the two domains, which can reserve semantic discrimination during adaptation. Specifically, in order to extract local-level features, we first dynamically construct local feature graphs on both domains and build a memory bank with the graphs from the source domain. In particular, we use optimal transport to generate the graph matching pairs. Then, based on the assignment matrix, we can align the feature distributions between the two domains with the graph-based local feature loss. Furthermore, we consider the correlation between the features of different categories and formulate a category-guided contrastive loss to guide the segmentation model to learn discriminative features on the target domain. Extensive experiments on different synthetic-to-real and real-to-real domain adaptation scenarios demonstrate that our method can achieve state-of-the-art performance. Our code is available at https://***/BianYikai/ PointUDA. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：