首页期刊导航|Pattern Recognition
期刊信息/Journal information
Pattern Recognition
Pergamon
Pattern Recognition

Pergamon

0031-3203

Pattern Recognition/Journal Pattern RecognitionSCIAHCIISTPEI
正式出版
收录年代

    LiDAR-based localization using universal encoding and memory-aware regression

    Yu, ShangshuWang, ChengWen, ChengluCheng, Ming...
    14页
    查看更多>>摘要：Visual localization is critical to many robotics and computer vision applications. Absolute pose regression performs localization by encoding scene features followed by pose regression, which has achieved impressive results in localization. It recovers 6-DoF poses from captured scene data alone. However, current methods suffer from being retrained with specific source data whenever the scene changes, resulting in expensive computational costs, data privacy disclosure, and unreliable localization caused by the inability to memorize all data. In this paper, we propose a novel LiDAR-based absolute pose regression network with universal encoding to avoid redundant retraining and the loss of data privacy. Specifically, we propose using universal feature encoding for different scenes. Only the regressor needs to be retrained to achieve higher efficiency, and the training is performed using the encoded features without source data, which preserves data privacy. Then, we propose a memory regressor for memory-aware regression, where the hidden unit numbers in the regressor determine the memorization capacity. It can be used to derive and improve the upper bound of the capacity to enable more reliable localization. Then, it is possible to modify the regressor structure to adapt different memorization capacity requirements for different scene sizes. Extensive experiments on outdoor and indoor datasets validated the above analyses and demonstrated the effectiveness of the proposed method.
      原文链接:
    • NSTL
    • Elsevier

    Expecting individuals' body reaction to Covid-19 based on statistical Naive Bayes technique

    Rabie, Asmaa H.Mansour, Nehal A.Saleh, Ahmed, ITakieldeen, Ali E....
    23页
    查看更多>>摘要：Covid-19, what a strange, unpredictable mutated virus. It has baffled many scientists, as no firm rule has yet been reached to predict the effect that the virus can inflict on people if they are infected with it. Recently, many researches have been introduced for diagnosing Covid-19; however, none of them pay attention to predict the effect of the virus on the person's body if the infection occurs but before the infection really takes place. Predicting the extent to which people will be affected if they are infected with the virus allows for some drastic precautions to be taken for those who will suffer from serious complications, while allowing some freedom for those who expect not to be affected badly. This paper introduces Covid-19 Prudential Expectation Strategy (CPES) as a new strategy for predicting the behavior of the person's body if he has been infected with Covid-19. The CPES composes of three phases called Outlier Rejection Phase (ORP), Feature Selection Phase (FSP), and Classification Phase (CP). For enhancing the classification accuracy in CP, CPES employs two proposed techniques for outlier rejection in ORP and feature selection in FSP, which are called Hybrid Outlier Rejection (HOR) method and Improved Binary Genetic Algorithm (IBGA) method respectively. In ORP, HOR rejects outliers in the training data using a hybrid method that combines standard division and Binary Gray Wolf Optimization (BGWO) method. On the other hand, in FSP, IBGA as a hybrid method selects the most useful features for the prediction process. IBGA includes Fisher Score (F-Score) as a filter method to quickly select the features and BGA as a wrapper method to accurately select the features based on the average accuracy value from several classification models as a fitness function to guarantee the efficiency of the selected subset of features with any classifier. In CP, CPES has the ability to classify people based on their bodies' reaction to Covid19 infection, which is built upon a proposed Statistical Naive Bayes (SNB) classifier after performing the previous two phases. CPES has been compared against recent related strategies in terms of accuracy, error, recall, precision, and run-time using Covid-19 dataset [1] . This dataset contains routine blood tests collected from people before and after their infection with covid-19 through a Web-based form created by us. CPES outperforms the competing methods in experimental results because it provides the best results with values of 0.87, 0.13, 0.84, and 0.79 for accuracy, error, precision, and recall.(C) 2022 Published by Elsevier Ltd.
      原文链接:
    • NSTL
    • Elsevier

    A feature consistency driven attention erasing network for fine-grained image retrieval

    Zhao, QiWang, XuLyu, ShuchangLiu, Binghao...
    12页
    查看更多>>摘要：Large-scale fine-grained image retrieval based hashing learning method has two main problems. First, low dimension feature embedding can fasten the retrieval process but bring accuracy decrease due to much information loss. Second, fine-grained images lead to the same category query hash codes mapping into the different cluster in database hash latent space. To handle these issues, we propose a feature con-sistency driven attention erasing network (FCAENet) for fine-grained image retrieval. For the first issue, we propose an adaptive augmentation module in FCAENet, which is the selective region erasing module (SREM). SREM makes the network more robust on subtle differences of fine-grained task by adaptively covering some regions of raw images. The feature extractor and hash layer can learn more representa-tive hash codes for fine-grained images by SREM. With regard to the second issue, we fully exploit the pair-wise similarity information and add the enhancing space relation loss (ESRL) in FCAENet to make the vulnerable relation stabler between the query hash code and database hash code. We conduct exten-sive experiments on five fine-grained benchmark datasets (CUB2011, Aircraft, NABirds, VegFru, Food101) for 12bits, 24bits, 32bits, 48bits hash codes. The results show that FCAENet achieves the state-of-the-art (SOTA) fine-grained image retrieval performance based on the hashing learning method.(c) 2022 Published by Elsevier Ltd.
      原文链接:
    • NSTL
    • Elsevier

    Quaternion-based weighted nuclear norm minimization for color image restoration

    Huang, ChaoyanLi, ZhiLiu, YubingWu, Tingting...
    15页
    查看更多>>摘要：Color image restoration is one of the basic tasks in pattern recognition. Unlike grayscale image, each color image has three channels in the RGB color space. Due to the inner-relationship within the three channels, color image restoration is usually much more difficult than its grayscale counterpart. Indeed, new problems such as color artifacts could emerge when the grayscale image processing methods are extended to color images directly. Note that one of the most effective gray image restoration methods is the weighted nuclear norm minimization (WNNM) approach. However, when applied to color images, the results of WNNM are usually not as promising as that of grayscale images. In order to solve this problem, in this paper, we propose to restore color images with the quaternion-based WNNM method (QWNNM) since the structure of color channels can be well preserved with quaternion representation. The proposed model can be solved efficiently by the alternating direction method of multipliers (ADMM). The theoretical analysis of the optimal solution is also presented. Numerical experiments are carefully conducted with different kinds of degradation to illustrate the superior performance of our proposed QWNNM over the state-of-the-art methods, including a celebrated deep learning approach, in both visual quality and numerical results. (c) 2022 Elsevier Ltd. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    SPARE: Self-supervised part erasing for ultra-fine-grained visual categorization

    Yu, XiaohanZhao, YangGao, Yongsheng
    11页
    查看更多>>摘要：This paper presents SPARE, a self-supervised part erasing framework for ultra-fine-grained visual categorization. The key insight of our model is to learn discriminative representations by encoding a self supervised module that performs random part erasing and prediction on the contextual position of the erased parts. This drives the network to exploit intrinsic structure of data, i.e., understanding and recognizing the contextual information of the objects, thus facilitating more discriminative part-level representation. This also enhances the learning capability of the model by introducing more diversified training part segments with semantic meaning. We demonstrate that our approach is able to achieve strong performance on seven publicly available datasets covering ultra-fine-grained visual categorization and finegrained visual categorization tasks. (c) 2022 Elsevier Ltd. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    Nakagami-Fuzzy imaging framework for precise lesion segmentation in MRI

    Alpar, OrcanDolezal, RafaelRyska, PavelKrejcar, Ondrej...
    17页
    查看更多>>摘要：Nakagami distribution and related imaging methods are very efficient in diagnostic ultrasonography for visualization and characterization of tissues for years. Abnormalities in tissues are distinguished from surrounding cells by application of the distribution ruled by the Nakagami m-parameter. The potential of discrimination in ultrasonography enables intelligent segmentation of lesions by other diagnostic tools and the imaging technique is very promising in other areas of medicine, like magnetic resonance imaging (MRI) for brain lesion identification, as presented in this paper. Therefore, we propose a novel NakagamiFuzzy imaging framework for intelligent and fully automated suspicious region segmentation from axial FLAIR MRI images exhibiting brain tumor characteristics to satisfy ground truth images with different precision levels. The images from MRI data set are processed by applying Nakagami distribution from pre-Rayleigh to post-Rayleigh for adjusting m-parameter. Amorphous and non-homogenous suspicious regions revealed by Nakagami imaging are segmented using customized Fuzzy 2-means to compare with two types of binary ground truths. The framework we propose is an outstanding example of fuzzy-based expert systems providing an average of 92.61% dice score for the main clinical experiment we conducted using the images and two types of ground truths provided by University of Hospital, Hradec Kralove. We also tested our framework by the BraTS 2012 and BraTS 2020 datasets and achieved an average of 91.88% and 89.25% dice scores respectively, which are competitive among the relevant researches.(c) 2022 Elsevier Ltd. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    Enhanced task attention with adversarial learning for dynamic multi-task CNN

    Fang, YuchunXiao, ShiweiZhou, MengluCai, Sirui...
    10页
    查看更多>>摘要：Multi-task deep learning is promising to solve multi-label multi-instance visual recognition tasks. How -ever, flexible information sharing in the task group might bring performance bottlenecks to an individual task. To tackle this problem, we propose a novel learning framework of multi-task Convolutional Neu-ral Network (CNN) to enhance task attention through conditionally tuning the Task Transfer Connections (TTC) with adversarial learning. For the dynamic multi-task CNN, we set up a shared subnet to extract shared features across multiple tasks and a task discriminator shared by all layers to distinguish features of all subnets. The adversarial training is introduced between the shared subnet and the task discrimi-nator to guide each task subnet to focus on its specific task. To apply adversarial learning to the com-plex labeling system of multiple tasks, we design an even-label strategy for the multi-task model with a shared subnet to make adversarial learning feasible for the complex labeling system of multiple tasks. As a result, the proposed model can constrain the shared subnet's learning unbiased to any single task and achieve task attention for all task subnets. Experimental results of the ablation study and the TTC analysis validate the effectiveness of the proposed approach.(c) 2022 Elsevier Ltd. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    Nonconvex clustering via l(0) fusion penalized regression

    Chen, HuangyueKong, LingchenLi, Yan
    12页
    查看更多>>摘要：Cluster analysis has attracted widespread attention in the past several decades. Generally speaking, clus-tering is considered as an important unsupervised learning method because its goal is to discover unknown subgroups in data without category label information. In this paper, we propose the l(0) fusion penalized clustering model (l(0)-PClust), which is a novel clustering framework founded on the penalized regression method. Theoretically, we first analyze the existence of the optimal solutions of our model and deduce an upper bound of the tuning parameter. Then we define the Karush-Kuhn-Tucker point and P-stationary point of the l(0)-PClust model, and establish the relationship between them and local optimal solutions. Moreover, based on the P-stationary point of the l(0)-PClust model, we prove that the distances among different cluster centers are greater than a positive threshold. Computationally, we solve the l(0)-PClust model via the famous alternating direction method of multipliers, whose limit point is a P-stationary point and local optimal solution of the model. Finally, we conduct extensive experiments on both synthetic and real data sets. Experimental results show outstanding performance of our method in comparison with several state-of-the-art clustering methods. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    Learning multi-level weight-centric features for few-shot learning

    Liang, MingjiangHuang, ShaoliPan, ShiruiGong, Mingming...
    11页
    查看更多>>摘要：Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the problem. However, they did not fully consider both the representation power for unseen categories and weight generation capacity in feature learning, making it a significant performance bottleneck. This paper proposes a multi-level weight-centric feature learning to give full play to feature extractor's dual roles in few-shot learning. Our proposed method consists of two essential techniques: a weight-centric training strategy to improve the features' prototype-ability and a multi-level feature incorporating a mid-and relation-level information. The former increases the feasibility of constructing a discriminative decision boundary based on a few samples. Simultaneously, the latter helps improve the transferability for characterizing novel classes and preserve classification capability for base classes. We extensively evaluate our approach to low-shot classification benchmarks. Experiments demonstrate our proposed method significantly outperforms its counterparts in both standard and generalized settings and using different network backbones.(c) 2022 Elsevier Ltd. All rights reserved.
      原文链接:
    • NSTL
    • Elsevier

    Node-Feature Convolution for Graph Convolutional Networks

    Zhang, LiSong, HedaAletras, NikolaosLu, Haiping...
    12页
    查看更多>>摘要：Graph convolutional network (GCN) is an effective neural network model for graph representation learn-ing. However, standard GCN suffers from three main limitations: (1) most real-world graphs have no regular connectivity and node degrees can range from one to hundreds or thousands, (2) neighboring nodes are aggregated with fixed weights, and (3) node features within a node feature vector are con -sidered equally important. Several extensions have been proposed to tackle the limitations respectively. This paper focuses on tackling all the proposed limitations. Specifically, we propose a new node-feature convolutional (NFC) layer for GCN. The NFC layer first constructs a feature map using features selected and ordered from a fixed number of neighbors. It then performs a convolution operation on this feature map to learn the node representation. In this way, we can learn the usefulness of both individual nodes and individual features from a fixed-size neighborhood. Experiments on three benchmark datasets show that NFC-GCN consistently outperforms state-of-the-art methods in node classification. (c) 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
      原文链接:
    • NSTL
    • Elsevier