检索结果-内蒙古大学图书馆

SDNet: Spatial adversarial perturbation local descriptor learned with the dynamic probabilistic weighting loss

NEUROCOMPUTING 2024年 601卷

作者： Huang, Kaiji Yang, Hua Jiang, Yuyang Yin, Zhouping Huazhong Univ Sci & Technol Wuhan Hubei Peoples R China

local descriptor is an important upstream component in computer vision tasks. Despite considerable advances with deep learning-based descriptors, recent descriptors are not robust enough to handle widespread viewpoint changes in image matching tasks such as localization and 3D reconstruction. In this study, SDNet, a robust descriptor utilizing spatial adversarial perturbations, trained with a novel dynamic probabilistic weighting to enhance performance under such challenges. First, to increase the robustness and generalization ability the network across spatially transformed instances, a innovative module for generating hard negative samples via spatial adversarial perturbations is designed. By maximizing adversarial loss, this module generates more complex patches, significantly enhancing the geometric robustness of the descriptor. Importantly, this module integrates seamlessly with existing patch-based descriptors without necessitating extra training data. Second, to mitigate the imbalance in the matching relationship between generated positive and negative pairs, the weighted triplet loss is proposed, which markedly improves descriptor performance. Third, a comprehensive theoretical analysis of preceding studies is carried out from a gradient perspective, and a probabilistic dynamic weighting approach that adaptively emphasizes weighting functions with higher likelihoods is proposed improve training performance of the descriptor. Extensive experiments are carried out on mainstream datasets. These comprehensive experiments demonstrate the effectiveness of SDNet, and the proposed method achieves significant improvements on the UBC, HPatches and ETH datasets, outperforming current state-of-the-art methods. The code is available at https://***/webd111/sdnet.

关键词： local descriptor Image matching Adversarial training Sample weighting Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Simple Task-Aware Contrastive local descriptor Selection Strategy for Few-Shot Learning Between Inter Class and Intra Class 33rd

A Simple Task-Aware Contrastive Local Descriptor Selection S...

引用

33rd International Conference on Artificial Neural Networks and Machine Learning (ICANN)

作者： Qiao, Qian Xie, Yu Huang, Shaoyao Li, Fanzhang Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Peoples R China

ISBN: (纸本)9783031723315;9783031723322

Few-shot image classification aims to classify novel classes with few labeled samples. Recent research indicates that deep local descriptors have better representational capabilities. These studies recognize the impact of background noise on classification performance. They typically filter query descriptors using all local descriptors in the support classes or engage in bidirectional selection between local descriptors in support and query sets. However, they ignore the fact that background features may be useful for the classification performance of specific tasks. This paper proposes a novel task-aware contrastive local descriptor selection network (TCDSNet). First, we calculate the contrastive discriminative score for each local descriptor in the support class, and select discriminative local descriptors to form a support descriptor subset. Finally, we leverage support descriptor subsets to adaptively select discriminative query descriptors for specific tasks. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on both general and fine-grained datasets.

关键词： few-shot learning task-aware local descriptor image classification

来源：评论

学校读者我要写书评

暂无评论

Shape binary patterns: an efficient local descriptor and keypoint detector for point clouds

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第3期81卷 3577-3601页

作者： Romero-Gonzalez, Cristina Garcia-Varea, Ismael Martinez-Gomez, Jesus Univ Castilla La Mancha Comp Syst Dept Campus Univ S-N Albacete 02071 Spain

Many of the research problems in robot vision involve the detection of keypoints, areas with salient information in the input images and the generation of local descriptors, that encode relevant information for such keypoints. Computer vision solutions have recently relied on Deep Learning techniques, which make extensive use of the computational capabilities available. In autonomous robots, these capabilities are usually limited and, consequently, images cannot be processed adequately. For this reason, some robot vision tasks still benefit from a more classic approach based on keypoint detectors and local descriptors. In 2D images, the use of binary representations for visual tasks has shown that, with lower computational requirements, they can obtain a performance comparable to classic real-value techniques. However, these achievements have not been fully translated to 3D images, where research is mainly focused on real-value approaches. Thus, in this paper, we propose a keypoint detector and local descriptor based on 3D binary patterns. The experimentation demonstrates that our proposal is competitive against state-of-the-art techniques, while its processing can be performed more efficiently.

关键词： Shape binary patterns Point clouds local descriptor Keypoint detector

来源：评论

学校读者我要写书评

暂无评论

local descriptor Generation Based on SIFT Reconstruction Transformation in Two Directions 12

Local Descriptor Generation Based on SIFT Reconstruction Tra...

引用

12th International Conference on Graphics and Image Processing (ICGIP)

作者： Ma, Qinyong Nie, Dongdong Yanshan Univ Coll Informat Sci & Engn Qinhuangdao 066004 Hebei Peoples R China Yanshan Univ Coll Sci Qinhuangdao 066004 Hebei Peoples R China

ISBN: (纸本)9781510642782;9781510642775

Image local feature descriptors are widely used in various classification and matching scenarios. Traditional local descriptors only extract features at specific scale. In order to improve the performance, some methods extract multi-scale and multi-angular features and construct descriptors by generalization, accumulation or ranking. However, the information of descriptors on bins and scales is not fully utilized, so there is a certain improvement space. To solve this problem, a method of constructing local descriptor based on two directions reconstruction transformation is proposed. Firstly, the stability of bins under different scale pairs is calculated, and then the stability of each bin relative to other bins is calculated. Then the cumulative gradient migration in scales direction is calculated, and the relative stability is combined into the score of a scale pair. The sum of the scores of all scale pairs of a bin constitutes the total score of the bin and eventually forms the vector of the descriptor. Experiments on two general datasets show that the accuracy of the proposed descriptor is improved without expanding the dimension.

关键词： SIFT local descriptor scale invariant bin gradient magnitude

来源：评论

学校读者我要写书评

暂无评论

Robust H_∞ deconvolution filtering of 2-D digital systems of orthogonal local descriptor

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第17期80卷 25965-25983页

作者： Mallahi, Mostafa El Boukili, Bensalem Zouhri, Amal Hmamed, Abdelaziz Qjidaa, Hassan Sidi Mohamed Ben Abdellah Univ High Normal Sch Dept Math & Comp Sci Lab Comp Sci & Interdisciplinary Phys Fes Morocco Sidi Mohamed Ben Abdellah Univ Fac Sci Dhar El Mahraz Dept Phys Comp Sci Signals Automat & Cognitivism Lab Fes Morocco

In this work, we propose a new set of H-infinity deconvolution filtering of 2-D color image using feature extraction of local descriptor and Fornasini-Machesini II (FM-II) model. The principal goal is to design 2-D deconvolution filter to reconstruct the noisy color image with the minimal information extracted from local Krawtchouk moment, Moreover, the filtering error system is asymptotically stable and satisfy the H-infinity performance index. the sufficient condition is given to ensure the H-infinity performance of the filtering error system through the Lyapunov theory, and the local Krawtckouk moment to give the feature extraction according to the order defined in advance instead of the global color image. Moreover, the 2-D deconvolution filter is designed to achieve the H-infinity performance index which the filter parameters are determined with certain optimization resolution. Finally, simulation example is provided to demonstrate the usefulness of the proposed design methods.

关键词： Deconvolution filtering 2-D systems H-infinity performance index Linear Matrix Inequality (LMI) Orthogonal polynomial local descriptor Color image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Face recognition with a new local descriptor based on strings of successive values (Aug, 10.1007/s11042-020-09400-9, 2020)

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第18期80卷 27045-27045页

作者： Zaaraoui, H. El Kaddouhi, S. Saaidi, A. Abarkan, M. Sidi Mohamed Ben Abdellah Univ Polydisciplinary Fac Taza Dept Math Phys & Comp Sci LSI BP 1223 Taza Morocco

In this paper, a novel face recognition approach based on strings of successive values (SSV) is presented. In contrast to most of the existing local descriptors which encode only a limited number of pixels included in a mask, the strings extract more discriminative information over the whole face region, by moving from the current pixel to the next one, and to the other next, and so on, according to the variations of their intensities. Therefore, the SSV can be stopped in any place of the face area, which allows us to encode more edge information and texture information than the existing methods. The proposed face recognition scheme requires several steps. Firstly, the images are divided into non-overlapping sub-regions from which the strings are extracted since each pixel produces two different strings. Thereafter, the dictionary of visual words is created to reduce the number of strings obtained from each patch of the image. Therefore, the face image is described only by visual words, because each string is replaced by its nearest dictionary word. As a result, the occurrence of visual words is computed in a histogram as a face descriptor. Finally, the recognition is performed by using the nearest neighbor classifier with the Hellinger distance. The effectiveness of the proposed approach is evaluated on three different databases, and the experimental results show that the recognition performances achieved are competitive or even outperform the literature state of the art methods.

关键词： Face recognition local descriptor Strings of successive values Levenshtein distance Hellinger distance

来源：评论

学校读者我要写书评

暂无评论

QSSR Modeling of Bacillus Subtilis Lipase A Peptide Collision Cross-Sections in Ion Mobility Spectrometry: local descriptor Versus Global descriptor

引用

PROTEIN JOURNAL 2021年第1期40卷 54-62页

作者： Ni, Zhong Wang, Anlin Kang, Lingyu Zhang, Tiancheng Jiangsu Univ Sch Life Sci Zhenjiang 212013 Jiangsu Peoples R China Fudan Univ Key Lab Reprod Regulat NPFPC Reprod & Dev Inst Shanghai Inst Planned Parenthood Res SIPPR Shanghai Peoples R China

To investigate the structure-dependent peptide mobility behavior in ion mobility spectrometry (IMS), quantitative structure-spectrum relationship (QSSR) is systematically modeled and predicted for the collision cross section omega values of totally 162 single-protonated tripeptide fragments extracted from the Bacillus subtilis lipase A. Two different types of structure characterization methods, namely, local and global descriptor as well as three machine learning methods, namely, partial least squares (PLS), support vector machine (SVM) and Gaussian process (GP), are employed to parameterize and correlate the structures and omega values of these peptide samples. In this procedure, the local descriptor is derived from the principal component analysis (PCA) of 516 physicochemical properties for 20 standard amino acids, which can be used to sequentially characterize the three amino acid residues composing a tripeptide. The global descriptor is calculated using CODESSA method, which can generate > 200 statistically significant variables to characterize the whole molecular structure of a tripeptide. The obtained QSSR models are evaluated rigorously via tenfold cross-validation and Monte Carlo cross-validation (MCCV). A comprehensive comparison is performed on the resulting statistics arising from the systematic combination of different descriptor types and machine learning methods. It is revealed that the local descriptor-based QSSR models have a better fitting ability and predictive power, but worse interpretability, than those based on the global descriptor. In addition, since the QSSR modeling using local descriptor does not consider the three-dimensional conformation of tripeptide samples, the method would be largely efficient as compared to the global descriptor.

关键词： Quantitative structure-spectrum relationship local descriptor Global descriptor Peptide Bacillus subtilis lipase A Ion mobility spectrometry

来源：评论

学校读者我要写书评

暂无评论

Automated semantic segmentation of bridge point cloud based on local descriptor and machine learning

引用

AUTOMATION IN CONSTRUCTION 2022年第0期133卷 103992-103992页

作者： Xia, Tian Yang, Jian Chen, Long Shanghai Jiao Tong Univ Sch Naval Architecture Ocean & Civil Engn Shanghai Key Lab Digital Maintenance Bldg & Infra Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ State Key Lab Ocean Engn Shanghai 200240 Peoples R China Lloyds Register Fdn Alan Turing Inst Data Centr Engn Programme London NW1 2DB England Loughborough Univ Sch Architecture Bldg & Civil Engn Loughborough LE11 3TU Leics England

In recent years, monitoring the health condition of existing bridges has become a common requirement. By providing an information management system, Bridge Information Model (BrIM) can highly improve the efficiency of health inspection and the reliability of condition evaluation. However, the current modeling processes still largely rely on manual work, where the cost outweighs the benefits. The main barrier lies in the challenging step of semantic segmentation of point clouds. Efforts have been made to identify and segment the structural components of bridges in existing research. But these methods are either dependent on manual data preprocessing or need big training dataset, which, however, has rendered them unpractical in real-world applications. This paper presents a combined local descriptor and machine learning based method to automatically detect structural components of bridges from point clouds. Based on the geometrical features of bridges, we design a multi-scale local descriptor, which is then used to train a deep classification neural network. In the end, a result refinement algorithm is adopted to optimize the segmentation results. Experiments on real-world reinforced concrete (RC) slab and beam-slab bridges show an average precision of 97.26%, recall of 98.00%, and intersection over union (IoU) of 95.38%, which significantly outperforms PointNet. This method has provided a potential solution to semantic segmentation of infrastructures by small sample learning and will contribute to the fulfillment of the automatic BrIM generation of typical highway bridges from the point cloud in the future.

关键词： Bridge information model Semantic segmentation local descriptor Machine learning Point cloud

来源：评论

学校读者我要写书评

暂无评论

local descriptor and Feature Selection Based Palmprint Recognition System 4th

Local Descriptor and Feature Selection Based Palmprint Recog...

引用

4th International Conference of Reliable Information and Communication Technology (IRICT)

作者： Taouche, Cherif Belhadef, Hacene Univ Oum El Bouaghi RELA CS2 Lab Oum El Bouaghi 04000 Algeria Univ Constantine 2 NTIC Fac Constantine 25016 Algeria

ISBN: (纸本)9783030335823;9783030335816

In this paper, we present a system based on a feature selection approach for solving the recognition problem in a multimodal biometric system combining both left and right palmprints of the same subject. In particular, the fusion of two or more traits, at feature-level, results in a long feature vector that needs large storage space, makes the execution time of the recognition task very long, and may include redundant and irrelevant features that can affect the recognition accuracy. To overcome these problems, feature selection is performed using genetic algorithms (GAs) and backtracking search algorithm for a comparison purpose. The experimental results show the usefulness of feature selection, especially the use of genetic algorithms, on the robustness of the multimodal biometric system as regards the feature vector length and run-time reduction, and the significant increase of the recognition rate.

关键词： Multimodal biometrics Feature selection local descriptor Palmprint recognition Feature-level fusion Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Critic Boosting Attention Network on local descriptor for Few-shot Learning

Critic Boosting Attention Network on Local Descriptor for Fe...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shi, Chengzhang Own, Chung-Ming Chou, Ching-chih Guo, Bailu Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China Nanning Normal Univ Sch Logist Management & Engn Nanning Peoples R China

ISBN: (纸本)9780738133669

Few-shot learning is a new upsurge of research in the computer vision field to adapt to new tasks with only a few examples. Recent works commonly use meta-learning or metric learning methods to solve the problem. In contrast, many of them usually use image-level feature representations and treat all parts of the image equally. This manipulation cannot cast off the cluttered background's interference or grasp the key-points of the idea rapidly. In our study, the authors use local descriptors assisted with image-to-class metric learning measures and utilize a critic following the human visual system mechanism to force the model to concentrate on the image's essential semantic parts. The unsupervised critic gives each of the local descriptors of an input image a score evaluating its significance and contribution to the final classification. Thus the model can relieve from the image background cluttering and fast focus on the essential parts. Generally, our proposed critic boosting attention network (short as CBAnet) can be classified as a kind of attention mechanism. Still, we do not need to use the background impact in an unsupervised way. The extensive experiments that we conduct on several benchmarks testify to our proposed method's superiority for few-shot learning.

关键词： Few-shot Learning local descriptor Critic Boosting Attention Network Deep Neural Network

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：