检索结果-内蒙古大学图书馆

Planning with learned dynamic model for unsupervised point cloud registration

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jiang, Haobo Qian, Jianjun 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 Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Point cloud registration is a fundamental problem in 3D computer vision. In this paper, we cast point cloud registration into a planning problem in reinforcement learning, which can seek the transformation between the source and target point clouds through trial and error. By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network. The transformation network aims to predict the new transformed feature of the point cloud after performing a rigid transformation (i.e., action) on it while the evaluation network aims to predict the alignment precision between the transformed source point cloud and target point cloud as the reward signal. Once the dynamic model of the point cloud is trained, we employ the cross-entropy method (CEM) to iteratively update the planning policy by maximizing the rewards in the point cloud registration process. Thus, the optimal policy, i.e., the transformation between the source and target point clouds, can be obtained via gradually narrowing the search space of the transformation. Experimental results on ModelNet40 and 7Scene benchmark datasets demonstrate that our method can yield good registration performance in an unsupervised manner. Copyright © 2021, The Authors. All rights reserved.

关键词： Dynamic models

Action candidate based clipped double Q-learning for discrete and continuous action tasks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： 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 Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Double Q-learning is a popular reinforcement learning algorithm in Markov decision process (MDP) problems. Clipped Double Q-learning, as an effective variant of Double Q-learning, employs the clipped double estimator to approximate the maximum expected action value. Due to the underestimation bias of the clipped double estimator, performance of clipped Double Q-learning may be degraded in some stochastic environments. In this paper, in order to reduce the underestimation bias, we propose an action candidate based clipped double estimator for Double Q-learning. Specifically, we first select a set of elite action candidates with the high action values from one set of estimators. Then, among these candidates, we choose the highest valued action from the other set of estimators. Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value. Theoretically, the underestimation bias in our clipped Double Q-learning decays monotonically as the number of the action candidates decreases. Moreover, the number of action candidates controls the trade-off between the overestimation and underestimation biases. In addition, we also extend our clipped Double Q-learning to continuous action tasks via approximating the elite continuous action candidates. We empirically verify that our algorithm can more accurately estimate the maximum expected action value on some toy environments and yield good performance on several benchmark problems. All code and hyperparameters available at https://***/Jiang-HB/AC CDQ. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

Supervised Adaptive-RPN Network for Object Detection in Remote Sensing images

学校读者我要写书评

暂无评论

Supervised Adaptive-RPN Network for Object Detection in Remo...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Xu Tang Huayu Zhang Jingjing Ma Xiangrong Zhang Licheng Jiao Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi'an Shaanxi Province China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Object detection is one of the most important tasks in the field of very high resolution (VHR) remote sensing (RS) images understanding. Due to the characteristics of VHR RS images, the detection performance is always limited by class imbalance and intersection-over-union (IoU) distribution imbalance. To mitigate the adverse effects caused thereby, we propose a supervised adaptive-RPN (SA-RPN) model with the help of deep learning in this paper. First, we introduced a supervised multi-dimensional attention network to overcome the foreground-background class imbalance. It can help the network to highlight the foreground and suppress the background effectively. Second, we develop the adaptive-RPN to reduce the negative impact of the IoU distribution imbalance by adaptively selecting the size of the anchor. The positive experimental results on the public data set validate the usefulness of our SA-RPN model. Compared with the popular deep learning RS object detection methods, our method achieves improved performance.

关键词： Object detection Adaptation models Feature extraction Remote sensing Proposals Training Sports

Deep Adaptive Proposal Network in Optical Remote Sensing images Objective Detection

学校读者我要写书评

暂无评论

Deep Adaptive Proposal Network in Optical Remote Sensing Ima...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Lingling Li Lin Cheng Xiaohui Guo Xu Liu Licheng Jiao Fang Liu Joint International Research Laboratory of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Xi'an China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

It is difficult to distinguish complicated distribution characteristics of objects, which limits the performance of two-stage detectors in the field of optical remote sensing images object detection. In this paper, we propose a deep adaptive proposal network (DAPNet), which is a new category prior network (CPN) on the basis of the existing faster region convolutional neural network (Faster RCNN) architecture. The adaptive candidate boxes for each image is obtained by combining the candidate regions and the object number, which are generated by the fine-region proposal network (F-RPN) and the CPN respectively. These adaptive candidate boxes can satisfy the detection tasks in sparse and dense scenes. A set of experimental results verify the superiority of the proposed approach.

关键词： Object detection Proposals Remote sensing Feature extraction Adaptive systems Detectors Optical sensors

A Cascaded LiDAR-Camera Fusion Network for Road Detection

学校读者我要写书评

暂无评论

A Cascaded LiDAR-Camera Fusion Network for Road Detection

IEEE International Conference on Robotics and Automation (ICRA)

作者： Shuo Gu Jian Yang Hui Kong 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 Nanjing China

Most of the existing road detection methods are either single-modal based, e.g., based on LiDAR or camera, or multi-modal based with LiDAR-camera fusion. The algorithms are designed for a specific data type, and cannot cope with input data changes. In addition, the LiDAR-camera based methods can only work in day time with enough light. In this paper, we develop a novel LiDAR-camera fusion strategy, which combines the LiDAR point clouds and the camera images in a cascaded way. The proposed network has two working modes, the single-modal mode with LiDAR point clouds only and the multimodal mode with both LiDAR and camera data, so it can be used in all day scenes. The whole network consists of three parts: 1) LiDAR segmentation module, which segments road points in the LiDAR’s imagery view. 2) Sparse-to-dense module, which upsamples the sparse LiDAR feature maps to dense road detection results. 3) LiDAR-camera fusion module, which fuses the dense LiDAR feature maps with the dense camera images to obtain accurate road estimations. Experiments on the KITTI-Road dataset show that the proposed cascaded LiDAR-camera fusion network can obtain very competitive road detection performance, with a MaxF value of 96.38%, and achieve the state-of-the-art in the single-modal mode among all LiDAR-only methods.

关键词： image segmentation Laser radar Automation Fuses Roads Conferences Estimation

Parametric Model Estimation for 3D Clothed Humans from Point Clouds

学校读者我要写书评

暂无评论

Parametric Model Estimation for 3D Clothed Humans from Point...

International Symposium on Mixed and Augmented Reality (ISMAR)

作者： Kangkan Wang Huayu Zheng Guofeng Zhang Jian Yang 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 State Key Laboratory of CAD&CG Zhejiang University China

This paper presents a novel framework to estimate parametric model- s for 3D clothed humans from partial point clouds. It is a challenging problem due to factors such as arbitrary human shape and pose, large variations in clothing details, and significant missing data. Existing methods mainly focus on estimating the parametric model of undressed bodies or reconstructing the non-parametric 3D shapes from point clouds. In this paper, we propose a hierarchical regression framework to learn the parametric model of detailed human shapes from partial point clouds of a single depth frame. Benefiting from the favorable ability of deep neural networks to model nonlinearity, the proposed framework cascades several successive regression networks to estimate the parameters of detailed 3D human body models in a coarse-to-fine manner. Specifically, the first global regression network extracts global deep features of point clouds to obtain an initial estimation of the undressed human model. Based on the initial estimation, the local regression network then refines the undressed human model by using the local features of neighborhood points of human joints. Finally, the clothing details are inferred as an additive displacement on the refined undressed model using the vertex-level regression network. The experimental results demonstrate that the proposed hierarchical regression approach can accurately predict detailed human shapes from partial point clouds and outperform prior works in the recovery accuracy of 3D human models.

关键词： Deep learning Solid modeling Three-dimensional displays Shape Clothing Estimation Predictive models

Learning to adapt via latent domains for adaptive semantic segmentation 21

学校读者我要写书评

暂无评论

Learning to adapt via latent domains for adaptive semantic s...

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Yunan Liu Shanshan Zhang Yang Li Jian Yang 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

ISBN: (纸本)9781713845393

Domain adaptive semantic segmentation aims to transfer knowledge learned from labeled source domain to unlabeled target domain. To narrow down the domain gap and ease adaptation difficulty, some recent methods translate source images to target-like images (latent domains), which are used as supplement or substitute to the original source data. Nevertheless, these methods neglect to explicitly model the relationship of knowledge transferring across different domains. Alternatively, in this work we break through the standard "source-target" one pair adaptation framework and construct multiple adaptation pairs (e.g. "source-latent" and "latent-target"). The purpose is to use the meta-knowledge (how to adapt) learned from one pair as guidance to assist the adaptation of another pair under a meta-learning framework. Furthermore, we extend our method to a more practical setting of open compound domain adaptation (a.k.a multiple-target domain adaptation), where the target is a compound of multiple domains without domain labels. In this setting, we embed an additional pair of "latent-latent" to reduce the domain gap between the source and different latent domains, allowing the model to adapt well on multiple target domains simultaneously. When evaluated on standard benchmarks, our method is superior to the state-of-the-art methods in both the single target and multiple-target domain adaptation settings.

关键词：

SSPC-Net: Semi-supervised semantic 3D point cloud segmentation network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cheng, Mingmei Hui, Le Xie, Jin Yang, Jian 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

Point cloud semantic segmentation is a crucial task in 3D scene understanding. Existing methods mainly focus on employing a large number of annotated labels for supervised semantic segmentation. Nonetheless, manually labeling such large point clouds for the supervised segmentation task is time-consuming. In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points. In our method, we first partition the whole point cloud into superpoints and build superpoint graphs to mine the long-range dependencies in point clouds. Based on the constructed superpoint graph, we then develop a dynamic label propagation method to generate the pseudo labels for the unsupervised superpoints. Particularly, we adopt a superpoint dropout strategy to dynamically select the generated pseudo labels. In order to fully exploit the generated pseudo labels of the unsupervised superpoints, we furthermore propose a coupled attention mechanism for superpoint feature embedding. Finally, we employ the cross-entropy loss to train the semantic segmentation network with the labels of the supervised superpoints and the pseudo labels of the unsupervised superpoints. Experiments on various datasets demonstrate that our semi-supervised segmentation method can achieve better performance than the current semi-supervised segmentation method with fewer annotated 3D points. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

Feature weighted non-negative matrix factorization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Mulin Gong, Maoguo Li, Xuelong The Academy of Advanced Interdisciplinary Research Xidian University Xi'an710071 China Northwestern Polytechnical University Xi'anShaanxi710072 China The Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education International Research Center for Intelligent Perception and Computation Xidian University Xi'anShaanxi710071 China Northwestern Polytechnical University Xi'an710072 China

Non-negative Matrix Factorization (NMF) is one of the most popular techniques for data representation and clustering, and has been widely used in machine learning and data analysis. NMF concentrates the features of each sample into a vector, and approximates it by the linear combination of basis vectors, such that the low-dimensional representations are achieved. However, in real-world applications, the features are usually with different importances. To exploit the discriminative features, some methods project the samples into the subspace with a transformation matrix, which disturbs the original feature attributes and neglects the diversity of samples. To alleviate the above problems, we propose the Feature weighted Non-negative Matrix Factorization (FNMF) in this paper. The salient properties of FNMF can be summarized as threefold: 1) it learns the weights of features adaptively according to their importances;2) it utilizes multiple feature weighting components to preserve the diversity;3) it can be solved efficiently with the suggested optimization algorithm. Performance on synthetic and real-world datasets demonstrate that the proposed method obtains the state-of-the-art performance. © 2021, CC BY-NC-ND.

关键词： Non-negative matrix factorization