检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shang, Ronghua Zhu, Songling Wu, Yinan Zhang, Weitong Jiao, Licheng Xu, Songhua The Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Shaanxi Province Xi’an710071 China The Department of Health Management Institute of Medical Artificial Intelligence The Second Affiliated Hospital of Xi’an Jiaotong University Xi’an China

Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing the compression rate and performance of the DNNs. However, due to its population-based nature, EMO pruning suffers from the complex optimization space and the resource-intensive structure verification process, especially in complex networks. To this end, a multi-objective complex network pruning framework based on divide-and-conquer and global performance impairment ranking (EMO-DIR) is proposed in this paper. Firstly, a divide-and-conquer EMO network pruning method is proposed, which decomposes the complex task of EMO pruning on the entire network into easier sub-tasks on multiple sub-networks. On the one hand, this decomposition narrows the pruning optimization space and decreases the optimization difficulty;on the other hand, the smaller network structure converges faster, so the proposed algorithm consumes lower computational resources. Secondly, a sub-network training method based on cross-network constraints is designed, which could bridge independent EMO pruning sub-tasks, allowing them to collaborate better and improving the overall performance of the pruned network. Finally, a multiple sub-networks joint pruning method based on EMO is proposed. This method combines the Pareto Fronts from EMO pruning results on multiple sub-networks through global performance impairment ranking to design a joint pruning scheme. The rich experiments on CIFAR-10/100 and imageNet-100/1k are conducted. The proposed algorithm achieves a comparable performance with the state-of-the-art pruning methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised image Captioning Considering Wasserstein Graph Matching

arXiv

引用

arXiv 2024年

作者： Yang, Yang The Nanjing University of Science and Technology Nanjing210094 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 Ministry of Education State Key Lab. for Novel Software Technology Nanjing University China

image captioning can automatically generate captions for the given images, and the key challenge is to learn a mapping function from visual features to natural language features. Existing approaches are mostly supervised ones, i.e., each image has a corresponding sentence in the training set. However, considering that describing images always requires a huge of manpower, we usually have limited amount of described images (i.e., image-text pairs) and a large number of undescribed images in real-world applications. Thereby, a dilemma is the "Semi-Supervised image Captioning". To solve this problem, we propose a novel Semi-Supervised image Captioning method considering Wasserstein Graph Matching (SSIC-WGM), which turns to adopt the raw image inputs to supervise the generated sentences. Different from traditional single modal semi-supervised methods, the difficulty of semi-supervised cross-modal learning lies in constructing intermediately comparable information among heterogeneous modalities. In this paper, SSIC-WGM adopts the successful scene graphs as intermediate information, and constrains the generated sentences from two aspects: 1) inter-modal consistency. SSIC-WGM constructs the scene graphs of the raw image and generated sentence respectively, then employs the wasserstein distance to better measure the similarity between region embeddings of different graphs. 2) intra-modal consistency. SSIC-WGM takes the data augmentation techniques for the raw images, then constrains the consistency among augmented images and generated sentences. Consequently, SSIC-WGM combines the cross-modal pseudo supervision and structure invariant measure for efficiently using the undescribed images, and learns more reasonable mapping function. Experiments show that our method can outperform state-of-the-art comparison methods on the MS-COCO "Karpathy" offline test split, under different complex semi-supervised scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism 7

Graph Convolutional Neural Network with Inter-layer Cascade ...

引用

7th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2021

作者： Wei, Lu Liu, Yiting Feng, Kaiyuan Li, Jianzhao Sheng, Kai Wu, Yue Xidian University Key Laboratory of Big Data and Intelligent Vision School of Computer Science and Technology Xi'an710071 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xi'an710071 China Academy of Advanced Interdisciplinary Research Xidian University Xi'an710071 China

ISBN: (纸本)9781665441490

In recent years, graph data in the non-Euclidean space has been widely used, and the methods and techniques for learning graph data in many deep learning fields have been continuously developed, such as the Graph neural network (GNN). The structural characteristics of graph data, the aggregation mode and representation mode of node information, and the node neighbor information are the core issues of GNN. However, most of the existing graph convolutional neural networks have an excessive smoothing problem, which limits the learning ability of the model. Aiming at the over-smoothing problem of the current algorithm, this paper enhances the learning of graph data by improving the expression ability of local information and global features. This paper constructs a cascade structure between graph convolutional layers. This kind of network structure realizes the dense connection of convolutional layers, makes the local feature information is effectively used, and further enhances the graph representation ability. Introduce self-attention and TopK into the Readout module, selectively aggregate and express feature information, and use graph-level information more efficiently. Graph classification is a downstream task to verify the performance of the proposed model. Experimental results prove that this densely structured graph convolutional network can effectively aggregate local node information and global graph-level information. © 2021 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Outlier Rejection for 3D Registration with Variational Bayes

arXiv

引用

arXiv 2023年

作者： Jiang, Haobo Dang, Zheng Wei, Zhen Xie, Jin Yang, Jian Salzmann, Mathieu CVLab EPFL Switzerland 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

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier feature representations. In this paper, we develop a novel variational non-local network-based outlier rejection framework for robust alignment. By reformulating the non-local feature learning with variational Bayesian inference, the Bayesian-driven long-range dependencies can be modeled to aggregate discriminative geometric context information for inlier/outlier distinction. Specifically, to achieve such Bayesian-driven contextual dependencies, each query/key/value component in our non-local network predicts a prior feature distribution and a posterior one. Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative. Thus, pushing the prior to be close to the discriminative posterior in the training step enables the features sampled from this prior at test time to model high-quality long-range dependencies. Notably, to achieve effective posterior feature guidance, a specific probabilistic graphical model is designed over our non-local model, which lets us derive a variational low bound as our optimization objective for model training. Finally, we propose a voting-based inlier searching strategy to cluster the high-quality hypothetical inliers for transformation estimation. Extensive experiments on 3DMatch, 3DLoMatch, and KITTI datasets verify the effectiveness of our method. Code is available at https://***/Jiang-HB/VBReg. Copyright © 2023, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Node Classification Based on Attribute Fuse Edge Features and Label Adaptive Adjustment

SSRN

引用

SSRN 2024年

作者： Shang, Ronghua Li, Ruolin Zhang, Weitong Xu, Songhua Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Shaanxi Xi’an710071 China Hangzhou Institute of Technology Xidian University Zhejiang Hangzhou311200 China Institute of Medical Artiffcial Intelligence the Second Afffliated Hospital of Xi’an Jiaotong University Shaanxi Xi’an710004 China

Most of existing graph representation learning methods only extract information from nodes and ignore the hidden information of edges. Nodes carry weak structural information thus affecting the specificity of node embeddings. To solve these problems, this paper proposes a node classification algorithm based on Attribute Fuse Edge Features and Label Adaptive Adjustment (AFEF_LAA). Firstly, Intimate-Relationship-Attribute of node is designed based on edge embeddings. Rz-Cos rule is constructed to perform the similarity metric between nodes and their neighbors to select intimate neighbor nodes. After that Reverse-TransE is constructed to encode embedding vectors of the edges connected to intimate neighborhood nodes. Secondly, a multi-fusion method based on smoothed neighborhood information is constructed. Each node in the original graph is smoothed together with its neighbor nodes. The smoothed original graph is multi-fused with multiple twin graphs. Finally, a strategy of label adaptive adjustment is proposed to select the label embedding vectors for input to the next-generation trainer by comparing accuracy. This strategy can improve the quality of graph embeddings while effectively avoiding the overfitting problem when processing highdimensional data. AFEF_LAA is compared with the state-of-the-art algorithms on six graph datasets. Experimental results show that AFEF_LAA can achieve higher node classification accuracy. © 2024, The Authors. All rights reserved.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection With Sky-Annotated Dataset

arXiv

引用

arXiv 2024年

作者： Xiao, Mengxuan Dai, Qun Zhu, Yiming Guo, Kehua Wang, Huan Shu, Xiangbo Yang, Jian Dai, Yimian School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China PCALab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security China School of Computer Science and Engineering Central South University China

Infrared small target detection poses unique challenges due to the scarcity of intrinsic target features and the abundance of similar background distractors. We argue that background semantics play a pivotal role in distinguishing visually similar objects for this task. To address this, we introduce a new task-clustered infrared small target detection, and present DenseSIRST, a novel benchmark dataset that provides per-pixel semantic annotations for background regions, enabling the transition from sparse to dense target detection. Leveraging this dataset, we propose the Background-Aware Feature Exchange Network (BAFE-Net), which transforms the detection paradigm from a single task focused on the foreground to a multi-task architecture that jointly performs target detection and background semantic segmentation. BAFE-Net introduces a dynamic cross-task feature hard-exchange mechanism to embed target and background semantics between the two tasks. Furthermore, we propose the Background-Aware Gaussian Copy-Paste (BAG-CP) method, which selectively pastes small targets into sky regions during training, avoiding the creation of false alarm targets in complex non-sky backgrounds. Extensive experiments validate the effectiveness of BAG-CP and BAFE-Net in improving target detection accuracy while reducing false alarms. The DenseSIRST dataset, code, and trained models are available at https://***/GrokCV/BAFE-Net. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Unified Density-Aware image Dehazing and Object Detection in Real-World Hazy Scenes 15th

Unified Density-Aware Image Dehazing and Object Detection in...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Zhengxi Zhao, Liang Liu, Yunan Zhang, Shanshan 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

ISBN: (纸本)9783030695378

It is an important yet challenging task to detect objects on hazy images in real-world applications. The major challenge comes from low visual quality and large haze density variations. In this work, we aim to jointly solve the image dehazing and the object detection tasks in real hazy scenarios by using haze density as prior knowledge. Our proposed Unified Dehazing and Detection (UDnD) framework consists of three parts: a residual-aware haze density classifier, a density-aware dehazing network, and a density-aware object detector. First, the classifier exploits the residuals of hazy images to accurately predict density levels, which provide rich domain knowledge for the subsequent two tasks. Then, we design respectively a High-Resolution Dehazing Network (HRDN) and a Faster R-CNN-based multi-domain object detector to leverage the extracted density information and tackle hazy object detection. Experiments demonstrate that UDnD performs favorably against other methods for object detection in real-world hazy scenes. Also, HRDN achieves better results than state-of-the-art dehazing methods in terms of PSNR and SSIM. Hence, HRDN can conduct haze removal effectively, based on which UDnD is able to provide high-quality detection results. © 2021, 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

Evolutionary Multi-Objective Overlapping Community Detection Based on Fusion of Internal and External Connectivity and Correction of Node Intimacy

SSRN

引用

SSRN 2022年

作者： Shang, Ronghua Wang, Sa Zhang, Weitong Feng, Jie Jiao, Licheng Stolkin, Rustam Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Shanxi Province Xi’an710071 China the Extreme Robotics Lab University of Birmingham United Kingdom

In the field of community detection, node attribute information plays an important role in community division. Most of the existing methods often use topology structure and node attribute information to discover non-overlapping communities, while attribute information has not been fully utilized in overlapping community detection. For this defect, this paper proposes an attribute information-assisted overlapping community detection method based on fusion of internal and external connectivity and correction of node intimacy in the framework of evolutionary multi-objective optimization (FC-CNIEA). Firstly, the initialization representation based on location and then label is supplemented by the fusion strategy based on internal and external connectivity, which integrates some communities with sparse internal connections and close external Connections. The number of communities is not only initially determined, but also reconfirmed and corrected. Secondly, a function is designed to calculate the intimacy between nodes, and the node label with the highest intimacy is selected to correct the current wrong node. The correction strategy is used in two stages of initialization and multi-objective evolution to obtain a more accurate node label. Finally, a method that considers not only the internal connection of the communities, but also the node attribute is designed to obtain the overlapping community indirectly from the non-overlapping community. The experimental results on five real networks and four classical synthetic networks show that compared with the four comparison algorithms, FC-CNIEA achieves better overlapping community division. © 2022, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label image Classification

引用

IEEE Transactions on Multimedia 2025年 27卷 3251-3265页

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Jiangsu Nanjing210094 China JD Explore Academy Beijing100000 China Anhui University School of Computer Science and Technology Anhui Heifei230601 China Yunnan University FIST LAB School of Information Science and Engineering Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this article, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice"in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also provide a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the potential of extending our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. © 1999-2012 IEEE.

关键词： image classification

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：