检索结果-内蒙古大学图书馆

Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fan, Xiaolong Gong, Maoguo Wu, Yue Zhang, Mingyang Li, Hao Jiang, Xiangming The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Shaanxi province Xi’an710071 China The School of Computer Science and Technology Xidian University Shaanxi province Xi’an710071 China

The empirical studies of Graph Neural Networks (GNNs) broadly take the original node feature and adjacency relationship as singleview input, ignoring the rich information of multiple graph views. To circumvent this issue, the multiview graph analysis framework has been developed to fuse graph information across views. How to model and integrate shared (i.e. consistency) and view-specific (i.e. complementarity) information is a key issue in multiview graph analysis. In this paper, we propose a novel Multiview Variational Graph Information Bottleneck (MVGIB) principle to maximize the agreement for common representations and the disagreement for view-specific representations. Under this principle, we formulate the common and view-specific information bottleneck objectives across multiviews by using constraints from mutual information. However, these objectives are hard to directly optimize since the mutual information is computationally intractable. To tackle this challenge, we derive variational lower and upper bounds of mutual information terms, and then instead optimize variational bounds to find the approximate solutions for the information objectives. Extensive experiments on graph benchmark datasets demonstrate the superior effectiveness of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Tri-Perspective view Decomposition for Geometry-Aware Depth Completion

学校读者我要写书评

暂无评论

Tri-Perspective view Decomposition for Geometry-Aware Depth ...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhiqiang Yan Yuankai Lin Kun Wang Yupeng Zheng Yufei Wang Zhenyu Zhang Jun Li 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 Sci. & Tech. China Huazhong University of Science and Technology Chinese Academy of Sciences Northwestem Poly technical University Nanjing University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Depth completion is a vital taskfor autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. How-ever, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this chal-lenge, we introduce Tri-Perspective View Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPVaffinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Fur-thermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sen-sor and the color camera on smart phones. Project page.

关键词： Geometry Point cloud compression Solid modeling Three-dimensional displays Laser radar Convolution Pattern recognition

Divide and Conquer: Hybrid Pre-training for Person Search

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tian, Yanling Chen, Di Liu, Yunan Yang, Jian Zhang, Shanshan 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 School of Artificial Intelligence Dalian Maritime University China

Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use imageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pretraining for person search, which involves detecting and reidentifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, finetuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community (https://***/personsearch/PretrainPS). Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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

学校读者我要写书评

暂无评论

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

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：

Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

学校读者我要写书评

暂无评论

Self-Supervised 3D Scene Flow Estimation Guided by Superpoin...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yaqi Shen Le Hui Jin Xie Jian Yang PCA Lab Nanjing University of Science and Technology Nanjing China 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

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D scenes for scene flow estimation. However, in existing methods, superpoints are generated with the offline clustering methods, which cannot characterize local regions with similar motions for complex 3D scenes well, leading to inaccurate scene flow estimation. To this end, we propose an iterative end-to-end super point based scene flow estimation framework, where the superpoints can be dynamically updated to guide the point-level flow prediction. Specifically, our framework consists of a flow guided superpoint generation module and a superpoint guided flow refinement module. In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds. With the generated superpoints, we first reconstruct the flow for each point by adaptively aggregating the superpoint-level flow, and then encode the consistency between the reconstructed flow of pairwise point clouds. Finally, we feed the consistency encoding along with the reconstructed flow into GRU to refine point-level flow. Extensive experiments on several different datasets show that our method can achieve promising performance. Code is available at https://***/supersyq/SPFlowNet.

关键词：

DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dai, Yimian Zou, Minrui Li, Yuxuan Li, Xiang Ni, Kang Yang, Jian The 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 Nanjing University of Posts and Telecommunications Nanjing China Key Laboratory of Radar Imaging and Microwave Photonics Nanjing University of Aeronautics and Astronautics Ministry of Education Nanjing China VCIP CS Nankai University China

Synthetic Aperture Radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive, ambiguous targets. While deep neural networks have advanced SAR target detection, their intrinsic low-frequency bias and static post-training weights falter with coherent noise and preserving subtle details across heterogeneous terrains. Motivated by traditional SAR image denoising, we propose DenoDet, a network aided by explicit frequency domain transform to calibrate convolutional biases and pay more attention to high-frequencies, forming a natural multiscale subspace representation to detect targets from the perspective of multi-subspace denoising. We design TransDeno, a dynamic frequency domain attention module that performs as a transform domain soft thresholding operation, dynamically denoising across subspaces by preserving salient target signals and attenuating noise. To adaptively adjust the granularity of subspace processing, we also propose a deformable group fully-connected layer (DeGroFC) that dynamically varies the group conditioned on the input features. Without bells and whistles, our plug-and-play TransDeno sets state-of-the-art scores on multiple SAR target detection datasets. The code is available at https://***/GrokCV/GrokSAR. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

Large motion video super-resolution with dual subnet and multi-stage communicated upsampling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Hongying Zhao, Peng Ruan, Zhubo Shang, Fanhua Liu, Yuanyuan Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China Peng Cheng Lab Shenzhen China

Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well concerned, summarized and utilized for guidance in a VSR algorithm. Especially, when a video contains large motion, conventional methods easily bring incoherent results or artifacts. In this paper, we propose a novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion. We design a new module named U-shaped residual dense network with 3D convolution (U3D-RDN) for fine implicit motion estimation and motion compensation (MEMC) as well as coarse spatial feature extraction. And we present a new Multi-Stage Communicated Upsampling (MSCU) module to make full use of the intermediate results of upsampling for guiding the VSR. Moreover, a novel dual subnet is devised to aid the training of our DSMC, whose dual loss helps to reduce the solution space as well as enhance the generalization ability. Our experimental results confirm that our method achieves superior performance on videos with large motion compared to state-of-the-art methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal sampling

学校读者我要写书评

暂无评论

Triple Point Masking

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Liu, Jiaming Kong, Linghe Wu, Yue Gong, Maoguo Li, Hao Miao, Qiguang Ma, Wenping Qin, Can The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Technology Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The College of Mathematics Science Inner Mongolia Normal University Hohhot010022 China The School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi’an710071 China The Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable plug- and-play framework for MAE pre-training to achieve multi-mask learning for 3D point clouds. Specifically, we augment the baseline methods with two additional mask choices (i.e., medium mask and low mask) as our core insight is that the recovery process of an object can manifest in diverse ways. Previous high-masking schemes focus on capturing the global representation information but lack fine-grained recovery capabilities, so that the generated pre-training weights tend to play a limited role in the fine-tuning process. With the support of the proposed TPM, current methods can exhibit more flexible and accurate completion capabilities, enabling the potential autoencoder in the pre-training stage to consider multiple representations of a single 3D point cloud object. In addition, during the fine-tuning stage, an SVM-guided weight selection module is proposed to fill the encoder parameters for downstream networks with the optimal weight, maximizing linear accuracy and facilitating the acquisition of intricate representations for new objects. Extensive experimental results and theoretical analysis show that five baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks. © 2025 IEEE. All rights reserved.

关键词： 3D modeling

Incremental Semi-Supervised Graph Learning Nmf with Block-Diagonal

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Lv, Xue Leng, Chengcai Cheng, Irene Basu, Anup Jiao, Licheng School of Mathematics Northwest University Xi’an710127 China Department of Computing Science University of Alberta EdmontonABT6G 2E8 Canada The Key Laboratory of Intelligent Perception and Image Understanding of Education Ministry of China School of Artificial Intelligence Xidian University Xi’an710071 China

Non-negative matrix factorization (NMF), as a good data dimensionality reduction method, is widely used in the field of image recognition. Incremental non-negative matrix factorization (INMF) as an improvement solves the problem of low efficiency caused by repeated running of data samples during online learning. However, in the traditional INMF algorithm, the newly added training samples do not contain label information. In an actual application scenario, there may be some samples being marked in both the initial sample and the new training sample. To fully utilize the small amount of label information carried by the dataset, we propose a semi-supervised NMF model for batch incremental data, namely incremental semi-supervised graph learning NMF with block-diagonal (ISGDNMF). The model is divided into three cases according to the degree of label-carrying for the new batch data: all label-carrying, no label-carrying and partial label-carrying. The label information is also used to add a diagonal structure to the coefficient matrix, which makes it possible to have a stronger discriminatory ability and be able to distinguish different classes of the images more easily. In addition, graph regularization information is added in order to maintain the spatial geometric structure of the data. Experiments on five image datasets illustrate that our algorithm has superior performance relative to seven other NMF-based algorithms. © 2023, The Authors. All rights reserved.

关键词： Non-negative matrix factorization