检索结果-内蒙古大学图书馆

Cross-layer navigation convolutional neural network for fine-grained visual classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Chenyu Xie, Jiyang Liang, Kongming Sun, Xian Ma, Zhanyu Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

Fine-grained visual classification (FGVC) aims to classify sub-classes of objects in the same super-class (e.g., species of birds, models of cars). For the FGVC tasks, the essential solution is to find discriminative subtle information of the target from local regions. Traditional FGVC models preferred to use the refined features, i.e., high-level semantic information for recognition and rarely use low-level information. However, it turns out that low-level information which contains rich detail information also has effect on improving performance. Therefore, in this paper, we propose cross-layer navigation convolutional neural network for feature fusion. First, the feature maps extracted by the backbone network are fed into a convolutional long short-term memory model sequentially from high-level to low-level to perform feature aggregation. Then, attention mechanisms are used after feature fusion to extract spatial and channel information while linking the high-level semantic information and the low-level texture features, which can better locate the discriminative regions for the FGVC. In the experiments, three commonly used FGVC datasets, including CUB-200-2011, Stanford-Cars, and FGVC-Aircraft datasets, are used for evaluation and we demonstrate the superiority of the proposed method by comparing it with other referred FGVC methods to show that this method achieves superior *** Codes 14J60 (Primary) 14F05, 14J26 (Secondary) Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Structured DropConnect for uncertainty inference in image classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zheng, Wenqing Xie, Jiyang Liu, Weidong Ma, Zhanyu Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China China Mobile Research Institute Beijing China Beijing Academy of Artificial Intelligence

With the complexity of the network structure, uncertainty inference has become an important task to improve classification accuracy for artificial intelligence systems. For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution. We introduce a DropConnect strategy on weights in the fully connected layers during training. In test, we split the network into several sub-networks, and then model the Dirichlet distribution by match its moments with the mean and variance of the outputs of these sub-networks. The entropy of the estimated Dirichlet distribution is finally utilized for uncertainty inference. In this paper, this framework is implemented on LeNet5 and VGG16 models for misclassification detection and out-of-distribution detection on MNIST and CIFAR-10 datasets. Experimental results show that the performance of the proposed SDC can be comparable to other uncertainty inference methods. Furthermore, the SDC is adapted well to different network structures with certain generalization capabilities and research *** Codes 14J60 (Primary) 14F05, 14J26 (Secondary) Copyright © 2021, The Authors. All rights reserved.

关键词： Image classification

TLRM: Task-level Relation Module for GNN-based Few-Shot Learning

学校读者我要写书评

暂无评论

TLRM: Task-level Relation Module for GNN-based Few-Shot Lear...

IEEE Visual Communications and Image Processing (VCIP)

作者： Yurong Guo Zhanyu Ma Xiaoxu Li Yuan Dong Pattern Recognition and Intelligent System Lab. Beijing University of Posts and Telecommunications Beijing China Beijing Academy of Artificial Intelligence Beijing China Lanzhou University of Technology Lanzhou China

ISBN: (纸本)9781728173221

Recently, graph neural networks (GNNs) have shown powerful ability to handle few-shot classification problem, which aims at classifying unseen samples when trained with limited labeled samples per class. GNN-based few-shot learning architectures mostly replace traditional metric with a learnable GNN. In the GNN, the nodes are set as the samples' embedding, and the relationship between two connected nodes can be obtained by a network, the input of which is the difference of their embedding features. We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks. That is, this method of measuring relation does not take the task-level information into account. To this end, we propose a new relation measure method, namely the task-level relation module (TLRM), to explicitly model the task-level relation of one sample to all the others. The proposed module captures the relation representations between nodes by considering the sample-to-task instead of sample-to-sample embedding features. We conducted extensive experiments on four benchmark datasets: mini-ImageNet, tiered-ImageNet, CUB-200-2011, and CIFAR-FS. Experimental results demonstrate that the proposed module is effective for GNN-based few-shot learning.

关键词： Measurement Visual communication Image processing Benchmark testing Graph neural networks Task analysis

Fgsd: A dataset for fine-grained ship detection in high resolution satellite images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Kaiyan Wu, Ming Liu, Jiaming Zhang, Chuang Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China

Ship detection using high-resolution remote sensing images is an important task, which contribute to sea surface regulation. The complex background and special visual angle make ship detection relies in high quality datasets to a certain extent. However, there is few works on giving both precise classification and accurate location of ships in existing ship detection datasets. To further promote the research of ship detection, we introduced a new fine-grained ship detection datasets, which is named as FGSD. The dataset collects high-resolution remote sensing images that containing ship samples from multiple large ports around the world. Ship samples were fine categorized and annotated with both horizontal and rotating bounding boxes. To further detailed the information of the dataset, we put forward a new representation method of ships orientation. For future research, the dock as a new class was annotated in the dataset. Besides, rich information of images were provided in FGSD, including the source port, resolution and corresponding GoogleEarth's resolution level of each image. As far as we know, FGSD is the most comprehensive ship detection dataset currently and it'll be available soon. Some baselines for FGSD are also provided in this paper. You are also welcome to contact us at ckyan@*** to get the dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Remote sensing

C-DLinkNet: Considering Multi-level semantic features for human parsing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lu, Yu Feng, Muyan Wu, Ming Zhang, Chuang Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing China

Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human. The challenge of human parsing is to extract effective semantic features to resolve deformation and multi-scale variations. In this work, we proposed an end-to-end model called C-DLinkNet based on LinkNet, which contains a new module named Smooth Module to combine the multi-level features in Decoder part. C-DLinkNet is capable of producing competitive parsing performance compared with the state-of-the-art methods with smaller input sizes and no additional information, i.e., achiving mIoU=53.05 on the validation set of LIP dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Wenjie Wang, Mei Zhang, Kai Li, Juncheng Li, Xiaoming Zhang, Yuhang Gao, Guangwei Deng, Weihong Lin, Chia-Wen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China The Computer Vision Lab ETH Zürich Zürich Switzerland The School of Communication and Information Engineering Shanghai University Shanghai China The Nanyang Technological University Singapore The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://***/24wenjie-li/Awesome-Face-Restoration. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

Graph Convolution Based Cross-Network Multi-Scale Feature Fusion for Deep Vessel Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Gangming Liang, Kongming Pan, Chengwei Zhang, Fandong Wu, Xianpeng Hu, Xinyang Yu, Yizhou The Department of Computer Science The University of Hong Kong Hong Kong Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Institute of Artificial Intelligence Beihang University Beijing China The AI Lab Deepwise Healthcare Beijing China Department of Cardiology of the Second Affiliated Hospital School of Medicine Zhejiang University Hangzhou China Key Laboratory of Cardiovascular of Zhejiang Province Hangzhou China

Vessel segmentation is widely used to help with vascular disease diagnosis. Vessels reconstructed using existing methods are often not sufficiently accurate to meet clinical use standards. This is because 3D vessel structures are highly complicated and exhibit unique characteristics, including sparsity and anisotropy. In this paper, we propose a novel hybrid deep neural network for vessel segmentation. Our network consists of two cascaded subnetworks performing initial and refined segmentation respectively. The second subnetwork further has two tightly coupled components, a traditional CNN-based U-Net and a graph U-Net. Cross-network multi-scale feature fusion is performed between these two U-shaped networks to effectively support high-quality vessel segmentation. The entire cascaded network can be trained from end to end. The graph in the second subnetwork is constructed according to a vessel probability map as well as appearance and semantic similarities in the original CT volume. To tackle the challenges caused by the sparsity and anisotropy of vessels, a higher percentage of graph nodes are distributed in areas that potentially contain vessels while a higher percentage of edges follow the orientation of potential nearby vessels. Extensive experiments demonstrate our deep network achieves state-of-the-art 3D vessel segmentation performance on multiple public and in-house datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anisotropy

Comparison of Backbones for Semantic Segmentation Network 5

学校读者我要写书评

暂无评论

Comparison of Backbones for Semantic Segmentation Network

2020 5th International Conference on intelligent Computing and Signal Processing, ICSP 2020

作者： Zhang, Rongyu Du, Lixuan Xiao, Qi Liu, Jiaming International School Beijing University of Post and Telecommunication Beijing100876 China International School of BusinessandFiance Sun Yat-Sen University Guangzhou510275 China Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications Beijing100876 China

As for the classification network that is constantly emerging with each passing day, different classification network as the backbone of the semantic segmentation network may show different performance. This paper selected the road extraction data set of CVPR DeepGlobe, and compared the performance differences of VGG-16 as the backbone of Unet, ResNet34, ResNet101 and Xception as the backbone of AD-LinkNet. When VGG-16 is used as the backbone of the semantic segmentation network, it performs better in the face of long and wide road extraction. As the backbone of the semantic segmentation network, ResNet has a higher ability to extract small roads. When Xception is used as the backbone of the semantic segmentation network, it not only retains the characteristics of ResNet34, but also can effectively deal with the complex situation of extracting target covered by occlusions. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Semantic Segmentation

Tracking system for driving assistance with the faster R-CNN 2nd

学校读者我要写书评

暂无评论

Tracking system for driving assistance with the faster R-CNN

2nd International Conference on Computer, Communication and Computational Sciences, IC4S 2017

作者： Yang, Kai Zhang, Chuang Wu, Ming Pattern Recognition and Intelligent System Lab School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9789811303432

The vehicle detection and tracking in driving assistance system are ordinarily achieved by the optical or radar technology. In this work, we explore video processing for driving assistance system. An object’s detection and tracking system based on the Faster R-CNN and Camshift algorithm is proposed, and Kalman filtering algorithm is used to predict the position of objects. Our system differs with other object-tracking algorithms based on deep learning, which directly detects each frame and has no tracking part, such as YOLO and SSD. We also introduce an evaluation criterion for driving assistance system according to the dangerous level of the surrounding cars. Through the experiments on the videos recorded by drive recorder, we show that our approach can achieve better performance in complex scenes than YOLO or SSD and can satisfy the real-time requirement by processing 30 frames per second. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Object detection