检索结果-内蒙古大学图书馆

Gaussian-induced convolution for graphs

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Jiang, Jiatao Cui, Zhen Xu, Chunyan 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

Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussian-induced convolution (GIC) framework to conduct local convolution filtering on irregular graphs. Specifically, an edge-induced Gaussian mixture model is designed to encode variations of subgraph region by integrating edge information into weighted Gaussian models, each of which implicitly characterizes one component of subgraph variations. In order to coarsen a graph, we derive a vertex-induced Gaussian mixture model to cluster vertices dynamically according to the connection of edges, which is approximately equivalent to the weighted graph cut. We conduct our multi-layer graph convolution network on several public datasets of graph classification. The extensive experiments demonstrate that our GIC is effective and can achieve the state-of-the-art results. Copyright © 2018, The Authors. All rights reserved.

关键词： Gaussian distribution

Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation

学校读者我要写书评

暂无评论

Cascaded Non-local Neural Network for Point Cloud Semantic S...

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Mingmei Cheng Le Hui Jin Xie 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

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

In this paper, we propose a cascaded non-local neural network for point cloud segmentation. The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. Specifically, we develop a novel cascaded non-local module, which consists of the neighborhood-level, superpoint-level and global-level non-local blocks. First, in the neighborhood-level block, we extract the local features of the centroid points of point clouds by assigning different weights to the neighboring points. The extracted local features of the centroid points are then used to encode the superpoint-level block with the non-local operation. Finally, the global-level block aggregates the non-local features of the superpoints for semantic segmentation in an encoder-decoder framework. Benefiting from the cascaded structure, geometric structure information of different neighborhoods with the same label can be propagated. In addition, the cascaded structure can largely reduce the computational cost of the original non-local operation on point clouds. Experiments on different indoor and outdoor datasets show that our method achieves state-of-the-art performance and effectively reduces the time consumption and memory occupation.

关键词： Three-dimensional displays Semantics Neural networks Stacking Memory management Feature extraction Computational efficiency

An Improved SSD for small target detection

学校读者我要写书评

暂无评论

An Improved SSD for small target detection

作者： Xiang Li Haibo LuoX Key Laboratory of Opt-Electronic Information Processing Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences The Key Laboratory of Image Understanding and Computer Vision

SSD is one of heuristic one-stage target detection *** it has got impressive results in general target detection,it still struggles in small-size object detection and precise *** this paper,we proposed an improved SSD which forces on the small-size target *** include a shallow and high resolution feature into the hierarchical detection feature which are used for ***,we fuse the detection features(including the shallow and high resolution one) as a feature pyramid through some 1 × 1 convolution layers and unsample operations to pass information from deep features to the shallow ones,aiming to enrich the semantic information of the shallow *** make the network easier to converge,we add a L2 normalization to the bottom detection feature of the feature pyramid to make a norm balance between each pyramid *** experimental results on the VEDAI dataset show that the proposed method has obtained impressive progress than the original SSD for the small targets detection.

关键词： Convolution neural network Target detection SSD Small targets

Multi-task learning for object keypoints detection and classification

学校读者我要写书评

暂无评论

Pattern Recognition Letters 2020年 130卷 182-188页

作者： Jie Xu Lin Zhao Shanshan Zhang Chen Gong 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 Nanjing 210094 China State Key Laboratory of Integrated Services Networks Xidian Univeristy Xi’an 710071 China

Object keypoints detection and classification are both central research topics in computer vision . Due to their wide range potential applications in the real world, substantial efforts have been taken to advance their performance. However, these two related tasks are mainly treated separately in previous works. We argue that keypoints detection and classification can be complementary tasks and beneficial to each other. Knowing the category of a object is able to reduce the searching space of keypoints detection models and facilitate more precise localization . On the other hand, having the knowledge of object keypoints can make classification models pay more attention on areas that are more associated with the object, which will inevitably promote classification accuracy . Embracing this observation, we propose to model keypoints detection and classification in a multi-task learning framework. Specifically, a multi-task deep network is designed and trained to conduct both tasks, where we devise the model structure delicately to carry out sufficient training of both tasks. Extensive experiments are set up on the AIFASHION DATASET and Human3.6M DATASET to validate our proposal, we show that our algorithm outperforms separate models trained individually on each task.

关键词：

Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cheng, Mingmei Hui, Le Xie, Jin Yang, Jian Kong, Hui 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 Nanjing210094 China

关键词： Semantic Segmentation

Fast Flow Reconstruction via Robust Invertible n × n Convolution

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Truong, Thanh-Dat Luu, Khoa Duong, Chi Nhan Le, Ngan Tran, Minh-Triet Computer Vision and Image Understanding Lab Department of Computer Science and Computer Engineering University of Arkansas Arkansas United States Department of Computer Science and Software Engineering Concordia University Quebec Canada Faculty of Information Technology University of Science VNU-HCM Ho Chi Minh Viet Nam

Flow-based generative models have recently become one of the most efficient approaches to model data generation. Indeed, they are constructed with a sequence of invertible and tractable transformations. Glow first introduced a simple type of generative flow using an invertible 1 × 1 convolution. However, the 1 × 1 convolution suffers from limited flexibility compared to the standard convolutions. In this paper, we propose a novel invertible n × n convolution approach that overcomes the limitations of the invertible 1 × 1 convolution. In addition, our proposed network is not only tractable and invertible but also uses fewer parameters than standard convolutions. The experiments on CIFAR-10, imageNet and Celeb-HQ datasets, have shown that our invertible n × n convolution helps to improve the performance of generative models significantly. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Haobo Lan, Kaihao Hui, Le Li, Guangyu 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 Nanjing210094 China

Learning robust feature matching between the template and search area is crucial for 3D Siamese tracking. The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization. In this paper, we propose a novel point cloud registration-driven Siamese tracking framework, with the intuition that spatially aligned corresponding points (via 3D registration) tend to achieve consistent feature representations. Specifically, our method consists of two modules, including a tracking-specific nonlocal registration module and a registration-aided Sinkhorn template-feature aggregation module. The registration module targets at the precise spatial alignment between the template and search area. The tracking-specific spatial distance constraint is proposed to refine the cross-attention weights in the nonlocal module for discriminative feature learning. Then, we use the weighted SVD to compute the rigid transformation between the template and search area, and align them to achieve the desired spatially aligned corresponding points. For the feature aggregation model, we formulate the feature matching between the transformed template and search area as an optimal transport problem and utilize the Sinkhorn optimization to search for the outlier-robust matching solution. Also, a registration-aided spatial distance map is built to improve the matching robustness in indistinguishable regions (e.g., smooth surface). Finally, guided by the obtained feature matching map, we aggregate the target information from the template into the search area to construct the target-specific feature, which is then fed into a CenterPoint-like detection head for object localization. Extensive experiments on KITTI, NuScenes and Waymo datasets verify the effectiveness of our proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization 37

学校读者我要写书评

暂无评论

A Single-Loop Accelerated Extra-Gradient Difference Algorith...

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Liu, Yuanyuan Shang, Fanhua An, Weixin Liu, Junhao Liu, Hongying Lin, Zhouchen 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 China Medical College Tianjin University China National Key Lab of General AI School of Intelligence Science and Technology Peking University China Institute for Artificial Intelligence Peking University China Peng Cheng Laboratory China

ISBN: (纸本)9781713899921

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 Oe(Ε-4), where Oe(·) hides logarithmic factors compared to O(·). As the special cases of the constrained NC-NC setting, the proposed algorithm can also obtain the same complexity O(Ε-2) for both the nonconvex-concave (NC-C) and convex-nonconcave (C-NC) cases, while the best-known complexity bounds are Oe(Ε-2.5) for the NC-C case and Oe(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 Oe(Ε-3) to O(Ε-2). To the best of our knowledge, this is the first time that the proposed algorithm improves the best-known complexity bounds from Oe(Ε-4) and Oe(Ε-3) to O(Ε-2) in both the NC-NC and NC-C settings. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Constrained optimization

Frequency-aware Interaction Network for Ultrasound image Segmentation

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2024年

作者： Wang, Dongfang Zhou, Tao Zhang, Yizhe Gao, Shangbing Yang, Jian Nanjing University Of Science And Technology Pca Lab Key Lab Of Intelligent Percept. And Syst. 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 Nanjing210094 China Huaiyin Institute Of Technology Faculty Of Computer And Software Engineering Huaian223003 China

Accurate segmentation of medical ultrasound images is crucial for guiding treatment decisions and assessing intervention effectiveness. The challenge of segmenting lesions in ultrasound images arises from factors such as low contrast, high speckle noise, artifacts, and blurred boundaries. Furthermore, this complexity varies significantly among lesions in different cases. While methods based on Convolutional Neural Networks (CNNs) and Transformers have shown promising results in this field, each approach possesses distinct advantages and limitations. To address these challenges, we propose a novel Frequency-aware Interaction Network (FINet). At the core of our FINet lies the proposed Multi-scale Frequency-aware Self-attention (MFS) module, which effectively captures multi-scale feature information within the self-attention layer. This enables our network to model both local and global features, capitalizing on the strengths of both CNNs and Transformers. Additionally, a frequency-aware network is introduced to learn the interactions between spatial locations in the frequency domain to enhance detailed feature representation such as edges. Furthermore, we present a collaborative interactive decoder network, in which a Selective Feature Interaction (SFI) module is proposed to facilitate the semantic and boundary feature interaction, resulting in more precise segmentation outcomes. Experimental results on four medical ultrasound image datasets show the superiority of our FINet over other state-of-the-art segmentation methods. More importantly, our model achieves an excellent trade-off between performance and computational efficiency. © 1991-2012 IEEE.

关键词： Ultrasonic imaging