23,126 Hits in 4.0 sec

Dimension reduction using collaborative representation reconstruction based projections

Juliang Hua, Huan Wang, Mingwu Ren, Heyan Huang
2016 Neurocomputing  
This paper develops a collaborative representation reconstruction based projections (CRRP) method for dimension reduction.  ...  Collaborative representation based classification (CRC) is much faster than sparse representation based classification (SRC) while owning the similar recognition performance to SRC.  ...  a SRC steered discriminant projections method (SRC-DP) for dimension reduction.  ... 
doi:10.1016/j.neucom.2016.01.060 fatcat:umdatgweyndchdb7nzwwerp6qa

Laplace Graph Embedding Class Specific Dictionary Learning for Face Recognition

Li Wang, Yan-Jiang Wang, Bao-Di Liu
2018 Journal of Electrical and Computer Engineering  
The sparse representation based classification (SRC) method and collaborative representation based classification (CRC) method have attracted more and more attention in recent years due to their promising  ...  Secondly, it gives different dictionary atoms with different weights to improve classification accuracy.  ...  The proposed LGECSDL algorithm is compared with another seven classical face recognition algorithms: nearest neighbor (NN) classification, collaborative representation based classification (CRC) [30]  ... 
doi:10.1155/2018/2179049 fatcat:fhimnv25svbbbnz3x6bt7p6ck4

Linear Discriminative Learning for Image Classification

Rab Nawaz Jadoon, Waqas Jadoon, Ahmad Khan, Zia ur Rehman, Sajid Shah, Iftikhar Ahmed Khan, WuYang Zhou
2019 Mathematical Problems in Engineering  
The resultant representation increases the discrimination ability for correct classification.  ...  In this paper, we propose a linear discriminative learning model called adaptive locality-based weighted collaborative representation (ALWCR) that formulates the image classification task as an optimization  ...  Waqas Jadoon for their continuous encouragement and massive support both academically and socially during this project. is work was sponsored by the key program of National Natural Science Foundation of  ... 
doi:10.1155/2019/4760614 fatcat:c4f5vfylojeblp3xhwofalleqq

TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning [article]

Shiming Chen, Ziming Hong, Guo-Sen Xie, Jian Zhao, Hao Li, Xinge You, Shuicheng Yan, Ling Shao
2021 arXiv   pre-print
Then, an attribute→visual decoder is employed to localize the image regions most relevant to each attribute in a given image for attribute-based visual feature representations.  ...  In this paper, we propose a cross attribute-guided Transformer network, termed TransZero++, to refine visual features and learn accurate attribute localization for semantic-augmented visual embedding representations  ...  and 2020-2022 Young Elite Scientist Sponsorship Program from China Association for Science and Technology YESS20200140.  ... 
arXiv:2112.08643v2 fatcat:jtickqje2var7i3vdncjpegjma

Adaptive collaborative graph for discriminant analysis of hyperspectral imagery

Zhen Ye, Rui Dong, Lin Bai, Yongjian Nian
2020 European Journal of Remote Sensing  
Recently, sparse graph-based discriminant analysis (SGDA) and collaborative graph-based discriminant analysis (CGDA) have been developed for dimensionality reduction of hyperspectral imagery.  ...  In order to preserve intrinsic geometrical structure of original data and improve the interpretability of the underlying graph, we propose an adaptive collaborative graph for discriminant analysis (ACGDA  ...  Ly for sharing the code of SGDA and CGDA.  ... 
doi:10.1080/22797254.2020.1735947 fatcat:qlztsfjbejaffmaxxtpantaena

A collaborative representation based projections method for feature extraction

Wankou Yang, Zhenyu Wang, Changyin Sun
2015 Pattern Recognition  
Like SPP, CRP aims to preserve the collaborative representation based reconstruction relationship of data. CRP utilizes a L2 norm graph to characterize the local compactness information.  ...  L2-graph calculates the edge weights using the total samples, avoiding manually choosing the nearest neighbors; second, a L2-graph based feature extraction method is presented, called collaborative representation  ...  And then a collaborative representation based classification (CRC) scheme is given for image recognition.  ... 
doi:10.1016/j.patcog.2014.07.009 fatcat:uyl4kfqhzfb7rbh7rqcerklio4

Task-driven Self-supervised Bi-channel Networks for Diagnosis of Breast Cancers with Mammography [article]

Ronglin Gong, Jun Wang, Jun Shi
2021 arXiv   pre-print
representation.  ...  In particular, a new gray-scale image mapping (GSIM) is designed as the pretext task, which embeds the class label information of mammograms into the image restoration task to improve discriminative feature  ...  In particular, the labels of binary classification is embedded into this task, and therefore, the learned feature representation contains discriminative information on benign and malignant mammograms,  ... 
arXiv:2101.06228v2 fatcat:sw7yesrukfe5tdq3lqla27kiie

Collaborative Attention Network for Person Re-identification [article]

Wenpeng Li, Yongli Sun, Jinjun Wang, Han Xu, Xiangru Yang, Long Cui
2020 arXiv   pre-print
have very limited capacity at extracting discriminative local patterns in the obtained feature representation.  ...  In this paper, we show that by explicitly learning the importance of small local parts and part combinations, we can further improve the final feature representation for Re-ID.  ...  In recent years, deep neural networks have been proven effective at extracting discriminative features for the images classification problem [2, 5, 7] , and are therefore widely used as base models of  ... 
arXiv:1911.13008v2 fatcat:h22l7nn7s5bornphlz7eza3qeu

Spatial‐spectral feature extraction of hyperspectral images using tensor‐based collaborative graph analysis

Lei Pan
2021 Electronics Letters  
Although the collaborative graph-based discriminant analysis (CGDA) method has shown promising performance for the feature extraction of the hyperspectral image (HSI), both the intrinsic local subspace  ...  To fully exploit the 3D spatial-spectral structural information, the collaborative representation model is extended to tensor space by using the third-order tensor representation of HSI, in which samples  ...  According to [10] , collaborative representation (CR) plays an important role in data representation.  ... 
doi:10.1049/ell2.12109 fatcat:nfikfiaxufa2hk4hqxx5ndfj2u

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects.  ...  Classification [17] CelebA, RaFD S Proposed a scalable image-to-image translation model among multiple domains using a single generator and a discriminator.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

Group Collaborative Learning for Co-Salient Object Detection [article]

Qi Fan, Deng-Ping Fan, Huazhu Fu, Chi Keung Tang, Ling Shao, Yu-Wing Tai
2021 arXiv   pre-print
To learn a better embedding space without extra computational overhead, we explicitly employ auxiliary classification supervision.  ...  We present a novel group collaborative learning framework (GCoNet) capable of detecting co-salient objects in real time (16ms), by simultaneously mining consensus representations at group level based on  ...  Simultaneously, a group collaborating module (GCM) is applied to enhance the image representation for discriminating the target attributes between different image groups.  ... 
arXiv:2104.01108v2 fatcat:3ibetbn7xrag7ogzmvmvysmnau

Collaborative Representation for SPD Matrices with Application to Image-Set Classification [article]

Li Chu, Rui Wang, Xiao-Jun Wu
2022 arXiv   pre-print
Collaborative representation-based classification (CRC) has demonstrated remarkable progress in the past few years because of its closed-form analytical solutions.  ...  Due to the space formed by a set of nonsingular covariance matrices is a well-known Symmetric Positive Definite (SPD) manifold, generalising the Euclidean collaborative representation to the SPD manifold  ...  Accordingly, a lower-dimensional and more discriminative subspace can be generated for image set classification.  ... 
arXiv:2201.08962v1 fatcat:vt7x3xglgnglfohpehj3jgwuya

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Panagiota Spyridonos, George Gaitanis, Aristidis Likas, Ioannis Bassukas
2021 Cancers  
Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images.  ...  Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive.  ...  A typical example is to repurpose pretrained embeddings trained on a large corpus of millions of images [34] for a large-scale classification task to implement a classification model for a different  ... 
doi:10.3390/cancers13246300 pmid:34944920 pmcid:PMC8699430 fatcat:zxa2hh3ykbh27cikqhjajndhoe

DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis [article]

Fatemeh Haghighi, Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang
2022 arXiv   pre-print
from unlabeled medical images for fine-grained semantic representation learning.  ...  Discriminative learning, restorative learning, and adversarial learning have proven beneficial for self-supervised learning schemes in computer vision and medical imaging.  ...  We thank them for their feasibility exploration, especially their initial evaluation on TransVW [26] and various training strategies.  ... 
arXiv:2204.10437v1 fatcat:pb6rumfdgzfnxhwrqbz76myozu

Collaborative and Low-Rank Graph for Discriminant Analysis of Hyperspectral Imagery

Chiranjibi Shah, Qian Du
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Sparse representation can be used for representation of a high-dimensional data into a low-dimensional subspace.  ...  In this paper, collaborative and low-rank representation-based discriminant analysis (CLGDA) is proposed, which is different from the concept of sparse representation.  ...  The resultant method is called collaborative and low-rank graph-embedding (CLGGE) for DR.  ... 
doi:10.1109/jstars.2021.3081398 fatcat:mm5k7ygs4jgyzlfpsn5con37pi
« Previous Showing results 1 — 15 out of 23,126 results