检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Zhilong Xiong Jia Cai Ranhui Yan Xiaolin Huang xFusion Digital Technologies Company Limited Shenzhen China School of Digital Economics Guangdong University of Finance & Economics Guangzhou China School of Statistics and Mathematics Guangdong University of Finance & Economics Guangzhou China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Graph neural networks (GNNs), as a powerful deep learning framework for modeling graph-structured data, have attracted lots of attention recently. Most of existing GNNs need a lot of labeled data. However, constructing generalizable and robust representation from unlabeled graph data remains a challenge for GNNs. Existing graph contrastive learning (GCL) methods either try to uniformly drop edges, or intend to remove unimportant nodes and edges, which heavily relies on the specific structure of the data. Another thing is that vanilla graph convolutional network only utilize low-pass filter (adjacency matrix), which ignores the middle and high frequency information of the graph structural data. To tackle existing challenges in the GCL methods, instead, we propose a noise perturbation based general GCL framework via flexible filters. Specifically, we first add various types of noise to the nodes and edges. Subsequently, we design flexible filters, which are the combination of low, middle and high-pass filters. Our investigation systematically examines the impact of noise and filters, with an initial theoretical analysis linking these elements to the triplet loss function, shedding light on their roles. Extensive experiments in node classification showcase that our proposed approach surpasses existing state-of-the-art baselines. Surprisingly, we find that moderate levels of noise effectively alleviate the over-smoothing problem encountered in GNNs, while the use of flexible filters notably enhances model performance.

关键词： Filters Sensitivity analysis Perturbation methods image processing image edge detection Noise Low-pass filters

来源：评论

学校读者我要写书评

暂无评论

FastFlowNet: A lightweight network for fast optical flow estimation

arXiv

引用

arXiv 2021年

作者： Kong, Lingtong Shen, Chunhua Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China The University of Adelaide Australia

Dense optical flow estimation plays a key role in many robotic vision tasks. It has been predicted with satisfying accuracy than traditional methods with advent of deep learning. However, current networks often occupy large number of parameters and require heavy computation costs. These drawbacks have hindered applications on power- or memory-constrained mobile devices. To deal with these challenges, in this paper, we dive into designing efficient structure for fast and accurate optical flow prediction. Our proposed FastFlowNet works in the well-known coarse-to-fine manner with following innovations. First, a new head enhanced pooling pyramid (HEPP) feature extractor is employed to intensify high-resolution pyramid feature while reducing parameters. Second, we introduce a novel center dense dilated correlation (CDDC) layer for constructing compact cost volume that can keep large search radius with reduced computation burden. Third, an efficient shuffle block decoder (SBD) is implanted into each pyramid level to acclerate flow estimation with marginal drops in accuracy. Experiments on both synthetic Sintel and real-world KITTI datasets demonstrate the effectiveness of proposed approaches, which consumes only 1/10 computation of comparable networks to get 90% of their performance. In particular, FastFlowNet only contains 1.37 M parameters and runs at 90 or 5.7 fps with one desktop NVIDIA GTX 1080 Ti or embedded Jetson TX2 GPU on Sintel resolution images. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation

FastFlowNet: A Lightweight Network for Fast Optical Flow Est...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Lingtong Kong Chunhua Shen Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China The University of Adelaide Australia

Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a large number of parameters and require heavy computation costs, largely hindering its application on low power-consumption devices such as mobile phones. In this paper, we tackle this challenge and design a lightweight model for fast and accurate optical flow prediction. Our proposed FastFlowNet follows the widely-used coarse-to-fine paradigm with following innovations. First, a new head enhanced pooling pyramid (HEPP) feature extractor is employed to intensify high-resolution pyramid features while reducing parameters. Second, we introduce a new center dense dilated correlation (CDDC) layer for constructing compact cost volume that can keep large search radius with reduced computation burden. Third, an efficient shuffle block decoder (SBD) is implanted into each pyramid level to accelerate flow estimation with marginal drops in accuracy. Experiments on both synthetic Sintel data and real-world KITTI datasets demonstrate the effectiveness of the proposed approach, which needs only ¹/10 computation of comparable networks to achieve on par accuracy. In particular, FastFlowNet only contains 1.37M parameters; and can execute at 90 FPS (with a single GTX 1080Ti) or 5.7 FPS (embedded Jetson TX2 GPU) on a pair of Sintel images of resolution 1024 × *** is available at: https://***/fastflow

关键词： Technological innovation Costs Head Correlation Estimation Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Object Detector based on Enhanced Multi-scale Feature Fusion Pyramid Network

Object Detector based on Enhanced Multi-scale Feature Fusion...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Luan Zhao Xiaofeng Zhang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Constructing the pyramidal architecture for the feature is currently a very effective way to obtain feature information of objects at different scales. Although the feature pyramid can realize the recognition and detection of multi-scale objects in the object detection task well, it still has some limitations. Since the feature information of different levels is often not from the same layer of the network, it is difficult to obtain the feature of different objects information at a certain scale from a certain level feature map of the pyramid network. To solve this problem, we present a novel object detection architecture, named Enhanced Multi-scale Feature Fusion Pyramid Network (EMFFPNet). Our network consists of Enhanced Multi-scale Feature Fusion Module (EMFFM) and Predictor Optimization Module (POM). In EMFFM, Features at different levels can be fused into the Enhanced features as outputs, which are more representative and deterministic. In order to enable the enhanced features to play their respective roles in the pyramid network, we assign different weights to fusion features of different levels in POM. We perform the experiments on the COCO detection benchmark. The experimental results indicate that the performance of our model is much better than the state-of-the-art model.

关键词： Object detection Predictive models Feature extraction Task analysis Information technology Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

SiamORPN: Enabling Orthogonality between Object and Background in Siamese Object Tracking

SiamORPN: Enabling Orthogonality between Object and Backgrou...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Kai Huang Chaolin Pan Jun Chu Lu Leng Jun Miao Junjiang Wu Lingfeng Wang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China School of Information Science and Technology Beijing University of Chemical Technology Beijing China

Siamese-based trackers currently are the dominant tracking paradigm due to the balance between speed and performance. However, it is prone to drift and tracking failure when the environment is complex and similar objects interfere. While the Siamese-based trackers perform the correlation operation, the responses of the target object and background appear in different channels, i.e., the feature spaces of the target object and background have some orthogonality. However, when meeting background clutters and similar objects interfere, this orthogonality becomes weaker and the wrong classification contribution of the object and the background reduces the stability of the learned similarity function, leading to many misclassified pixels in the heatmaps. In this work, we proposed a SiamORPN to solve the above issues. It is incorporated at two levels: an Orthogonal Region Proposal Network (ORPN) and an Adaptive Pixel-wise Aggregation (APA) module. Specifically, for ORPN, the orthogonality between the object and the background maximizes the inter-class inertia. Moreover, the ORPN introduces the orthogonal module to enhance this orthogonality. For APA, it introduces two lightweight networks to predict the weights of all pixels in different heatmaps and the weights of all pixels in different regression offsets. Experiments on challenging benchmarks, including OTB2015, VOT2016, VOT2018, GOT-10k test set, UAV123, LaSOT, and TrackingNet, demonstrate the proposed SiamORPN outperforms many SOTA trackers and achieves leading performance. The inference speed at GTX1080Ti can reach about 32 FPS, meeting the real-time requirements.

关键词： Heating systems Target tracking Correlation Adaptive systems Benchmark testing Real-time systems Proposals

来源：评论

学校读者我要写书评

暂无评论

Consistency-Guided Adaptive Alternating Training for Semi-Supervised Salient Object Detection

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Liyuan Liu, Wei Wang, Hua Jeon, Sang-Woon Jiang, Yunliang Zheng, Zhonglong Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Department of Automation Shanghai200240 China Victoria University Institute for Sustainable Industries and Liveable Cities College of Engineering and Science MelbourneVIC8001 Australia Hanyang University Department of Electrical and Electronic Engineering Ansan Korea Republic of

This paper presents a novel approach that leverages two models to integrate features from numerous unlabeled images, addressing the challenge of semi-supervised salient object detection (SSOD). Unlike conventional methods that rely on selecting high-quality pseudo labels, our method identifies the model that produces consistent predictions for original images and their color transformation versions from two models to infer reliable pseudo labels for all unlabeled images, improving the diversity of the training set. Specifically, we propose adaptive selection indicators to quantify prediction differences and guide the updates of the two models using the unlabeled set alternatively. Initially, two models used in our framework are trained on the labeled set. Once the adaptive selection indicator conditions are satisfied, one model is designated as the proxy, generating pseudo labels, while the other serves as the saliency model, which is further trained using these pseudo labels. Subsequently, the updated saliency model optimizes the proxy model's parameters according to another adaptive selection indicator. Experimental results and ablation studies on six benchmark salient object detection datasets confirm the effectiveness and robustness of our method. Our approach achieves performance comparable to recent fully supervised methods while using only one eighth of the labeled data, demonstrating its potential for efficient and scalable SSOD. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data-Free Knowledge Distillation

arXiv

引用

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Difference Learning for Noisy Rigid image Alignment

arXiv

引用

arXiv 2022年

作者： Chen, Yu-Xuan Feng, Dagan Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China School of Computer Science University of Sydney Sydney2006 Australia

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer networks show an improved performance on clean images but will not achieve satisfactory performance on noisy images due to its heavy reliance on pixel value comparations. To handle such challenging applications, we report a new unsupervised difference learning (UDL) strategy and apply it to rigid image alignment. UDL exploits the quantitative properties of regression tasks and converts the original unsupervised problem to pseudo supervised problem. Under the new UDL-based image alignment pipeline, rotation can be accurately estimated on both clean and noisy images and translations can then be easily solved. Experimental results on both nature and cryo-EM images demonstrate the efficacy of our UDL-based unsupervised rigid image alignment method. Copyright © 2022, The Authors. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Application of an Improved Focal Loss in Vehicle Detection 19th

Application of an Improved Focal Loss in Vehicle Detection

引用

19th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2020

作者： He, Xuanlin Yang, Jie Kasabov, Nikola Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Auckland University of Technology Auckland New Zealand

ISBN: (纸本)9783030614003

Object detection is an important and fundamental task in computer vision. Recently, the emergence of deep neural network has made considerable progress in object detection. Deep neural network object detectors can be grouped in two broad categories: the two-stage detector and the one-stage detector. One-stage detectors are faster than two-stage detectors. However, they suffer from a severe foreground-backg-round class imbalance during training that causes a low accuracy performance. RetinaNet is a one-stage detector with a novel loss function named Focal Loss which can reduce the class imbalance effect. Thereby RetinaNet outperforms all the two-stage and one-stage detectors in term of accuracy. The main idea of focal loss is to add a modulating factor to rectify the cross-entropy loss, which down-weights the loss of easy examples during training and thus focuses on the hard examples. However, cross-entropy loss only focuses on the loss of the ground-truth classes and thus it can’t gain the loss feedback from the false classes. Thereby cross-entropy loss does not achieve the best convergence. In this paper, we proposed a new loss function named Dual Cross-Entropy Focal Loss, which improves on the focal loss. Dual cross-entropy focal loss adds a modulating factor to rectify the dual cross-entropy loss towards focusing on the hard samples. Dual cross-entropy loss is an improved variant of cross-entropy loss, which gains the loss feedback from both the ground-truth classes and the false classes. We changed the loss function of RetinaNet from focal loss to our dual cross-entropy focal loss and performed some experiments on a small vehicle dataset. The experimental results show that our new loss function improves the vehicle detection performance. © 2020, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

CDFI: Cross Domain Feature Interaction for Robust Bronchi Lumen Detection

CDFI: Cross Domain Feature Interaction for Robust Bronchi Lu...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jiasheng Xu Tianyi Zhang Yangqian Wu Jie Yang Guang–Zhong Yang Yun Gu Institute of Medical Robotics Shanghai Jiao Tong University Shanghai CHINA Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai CHINA MOE Key Laboratory of System Control and Information Processing Shanghai P.R. China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai China

Endobronchial intervention is increasingly used as a minimally invasive means for the treatment of pulmonary diseases. In order to reduce the difficulty of manipulation in complex airway networks, robust lumen detection is essential for intraoperative guidance. However, these methods are sensitive to visual artifacts which are inevitable during the surgery. In this work, a cross domain feature interaction (CDFI) network is proposed to extract the structural features of lumens, as well as to provide artifact cues to characterize the visual features. To effectively extract the structural and artifact features, the Quadruple Feature Constraints (QFC) module is designed to constrain the intrinsic connections of samples with various imaging-quality. Furthermore, we design a Guided Feature Fusion (GFF) module to supervise the model for adaptive feature fusion based on different types of artifacts. Results show that the features extracted by the proposed method can preserve the structural information of lumen in the presence of large visual variations, bringing much-improved lumen detection accuracy.

关键词：

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：