Filters








11,285 Hits in 7.1 sec

Unsupervised Feature Learning for low-level Local Image Descriptors [article]

Christian Osendorfer and Justin Bayer and Sebastian Urban and Patrick van der Smagt
2013 arXiv   pre-print
However, it has never been quantitatively investigated yet how well unsupervised learning methods can find low-level representations for image patches without any additional supervision.  ...  Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision.  ...  find good low-level image descriptors.  ... 
arXiv:1301.2840v4 fatcat:bsh4bghcmng5nd25kw4lntfn7u

Unsupervised Learning for Satellite Image Classification

Giriraja C.V, Srinivasa C, T.K. Jaya Ram, Avula Haswanth
2014 IOSR Journal of VLSI and Signal processing  
The low-level feature descriptors are encoded in terms of the basis functions to generate new sparse representation for the feature descriptors.  ...  Dense low-level feature descriptors are extracted and exploited in a novel way to learn a set of basis functions.  ...  We are also very grateful for the comments made by the Principal, HOD of the department, faculties etc., their input helped in improving the quality of the final version of this paper.  ... 
doi:10.9790/4200-04240104 fatcat:pj5vigcrfnecbfrp2ryne3ugka

Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines [chapter]

Hanlin Goh, Nicolas Thome, Matthieu Cord, Joo-Hwee Lim
2012 Lecture Notes in Computer Science  
Recently, the coding of local features (e.g. SIFT) for image categorization tasks has been extensively studied.  ...  Firstly, we steer the unsupervised RBM learning using a regularization scheme, which decomposes into a combined prior for the sparsity of each feature's representation as well as the selectivity for each  ...  The first is the design of powerful low-level local descriptors, such as SIFT [1] .  ... 
doi:10.1007/978-3-642-33715-4_22 fatcat:vjoe6a7qlrdoxhlm424gnptu6y

Improved bag-of-words model for person re-identification

Lu Tian, Shengjin Wang
2018 Tsinghua Science and Technology  
Most existing methods are based on supervised learning which requires a large number of labeled data. In this paper, we develop a robust unsupervised learning approach for person re-id.  ...  The proposed descriptor does not require any re-id labels, and is robust against pedestrian variations. Experiments show the proposed iBoW descriptor outperforms other unsupervised methods.  ...  [37] , local experts were considered to learn a common feature space for person reidentification across views.  ... 
doi:10.26599/tst.2018.9010060 fatcat:iedzjban5zbkvjf6wz7dghydri

Review of Local Descriptor in RGB-D Object Recognition

Ema Rachmawati, Iping Supriana Suwardi, Masayu Leylia Khodra
2014 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
We review the use of local descriptors as the feature representation which is extracted from RGB-D images, in instances and category-level object recognition.  ...  We also highlight the involvement of depth images and how they can be combined with RGB images in constructing a local descriptor.  ...  Various methods to learn low-level features from raw data (feature learning) have been produced by the machine learning community, i.e.  ... 
doi:10.12928/telkomnika.v12i4.388 fatcat:4rdsur3agfbg3b57boz3xoasxq

Metric Learning in Codebook Generation of Bag-of-Words for Person Re-identification [article]

Lu Tian, Shengjin Wang
2017 arXiv   pre-print
The Bag-of-Words (BoW) model is a widely used image representing descriptor in part one. Its codebook is simply generated by clustering visual features in Euclidian space.  ...  With several low level features extracted on superpixel and fused together, our method outperforms state-of-the-art on person re-identification benchmarks including VIPeR, PRID450S, and Market1501.  ...  for low level features; 3) we integrate the proposed local feature level metric learning method with conventional part two image descriptor level metric learning methods and achieve state-of-the-art results  ... 
arXiv:1704.02492v2 fatcat:k4n5wzrexfdu5mov72khgimveu

Learning Deep Hierarchical Visual Feature Coding

Hanlin Goh, Nicolas Thome, Matthieu Cord, Joo-Hwee Lim
2014 IEEE Transactions on Neural Networks and Learning Systems  
The low-level representations of descriptors that were learned using this method result in generic features that we empirically found to be transferrable between different image datasets.  ...  Local gradient-based descriptors, such as SIFT, are encoded via a hierarchical coding scheme composed of spatial aggregating restricted Boltzmann machines (RBM).  ...  Airplane Bicycle Car Cat Chair Dog House Person High--Level Image Signature Pooling Coding Coding Low--Level Local Descriptors Mid--Level Hierarchical Visual Codes Feature Extrac  ... 
doi:10.1109/tnnls.2014.2307532 pmid:25420244 fatcat:unxxneak2bbwxghxz2ijqmlwry

Breast image feature learning with adaptive deconvolutional networks

Andrew R. Jamieson, Karen Drukker, Maryellen L. Giger, Bram van Ginneken, Carol L. Novak
2012 Medical Imaging 2012: Computer-Aided Diagnosis  
In this preliminary study, we explored the use of Adaptive Deconvolutional Networks (ADN) for learning high-level features in diagnostic breast mass lesion images with potential application to computer-aided  ...  An alternative approach is to learn features directly from images.  ...  The authors are grateful to Matthew Zeiler and Migeul Carreira-Perpiñán for making their useful code available online.  ... 
doi:10.1117/12.910710 dblp:conf/micad/JamiesonDG12 fatcat:25h5a4zfe5dizlnrdse4vfgyua

A Survey on Content-based Image Retrieval

Mohamed Maher
2017 International Journal of Advanced Computer Science and Applications  
Namely, unsupervised and supervised learning and fusion techniques along with lowlevel image visual descriptors have been reported.  ...  The widespread of smart devices along with the exponential growth of virtual societies yield big digital image databases.  ...  The author is grateful for this support.  ... 
doi:10.14569/ijacsa.2017.080521 fatcat:kzfskamd25coxcj3537z6z3ty4

Automatic Diagnosis of Ovarian Carcinomas via Sparse Multiresolution Tissue Representation [chapter]

Aïcha BenTaieb, Hector Li-Chang, David Huntsman, Ghassan Hamarneh
2015 Lecture Notes in Computer Science  
Our novel approach uses an unsupervised feature learning framework composed of a sparse tissue representation and a discriminative feature encoding scheme.  ...  This new grading scheme for ovarian carcinomas results in a low to moderate interobserver agreement among pathologists.  ...  Acknowledgment: We would like to thank NSERC for their financial support and our collaborators at the British Columbia Cancer Agency for providing insight and expertise that greatly assisted the research  ... 
doi:10.1007/978-3-319-24553-9_77 fatcat:27nyvav375eanbfrjg3sgeymqm

Foreground Focus: Finding Meaningful Features in Unlabeled Images

Y.J. Lee, K. Grauman
2008 Procedings of the British Machine Vision Conference 2008  
We show that this mutual reinforcement of object-level and feature-level similarity improves unsupervised image clustering, and apply the technique to automatically discover categories and foreground regions  ...  Our method first computes an initial image-level grouping based on feature correspondences, and then iteratively refines cluster assignments based on the evolving intra-cluster pattern of local matches  ...  We would like to thank David Liu and Delbert Dueck for sharing their experimental data.  ... 
doi:10.5244/c.22.52 dblp:conf/bmvc/LeeG08 fatcat:cpnpmyn3p5euxlyqftqvjh7v54

Learning Deep Binary Descriptor with Multi-quantization

Yueqi Duan, Jiwen Lu, Ziwei Wang, Jianjiang Feng, Jie Zhou
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose an unsupervised feature learning method called deep binary descriptor with multiquantization (DBD-MQ) for visual matching.  ...  Extensive experimental results on different visual analysis including patch retrieval, image matching and image retrieval show that our DBD-MQ outperforms most existing binary feature descriptors.  ...  Inspired by the fact that CNN features deliver strong discriminative power and binary features present low computational cost, DeepBit [26] learns deep compact binary descriptors in an unsupervised manner  ... 
doi:10.1109/cvpr.2017.516 dblp:conf/cvpr/DuanLWFZ17 fatcat:wzqgayi7drfr5oacakk24abnba

PatternNet: A benchmark dataset for performance evaluation of remote sensing image retrieval

Weixun Zhou, Shawn Newsam, Congmin Li, Zhenfeng Shao
2018 ISPRS journal of photogrammetry and remote sensing (Print)  
These limitations have severely restricted the development of novel feature representations for RSIR, particularly the recent deep-learning based features which require large amounts of training data.  ...  We also provide a thorough review of RSIR approaches ranging from traditional handcrafted feature based methods to recent deep learning based ones.  ...  Acknowledgements The authors would like to thank Paolo Napoletano for the code used in the performance evaluation.  ... 
doi:10.1016/j.isprsjprs.2018.01.004 fatcat:v5oei4amy5a4nbqklertcg74lm

Unsupervised Feature Learning by Deep Sparse Coding [chapter]

Yunlong He, Koray Kavukcuoglu, Yun Wang, Arthur Szlam, Yanjun Qi
2014 Proceedings of the 2014 SIAM International Conference on Data Mining  
In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks  ...  As a result, the new method is able to learn multiple layers of sparse representations of the image which capture features at a variety of abstraction levels and simultaneously preserve the spatial smoothness  ...  While most of the previous works use SIFT features of image patches, TFM [18] proposed new locally-invariant feature descriptors that are learned from raw images automatically in an unsupervised fashion  ... 
doi:10.1137/1.9781611973440.103 dblp:conf/sdm/HeKWSQ14 fatcat:5m5tbo5tkbc77du4vw3z3p2olu

Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks

Kevin Lin, Jiwen Lu, Chu-Song Chen, Jie Zhou
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching.  ...  Unlike most existing binary descriptors which were designed with random projections or linear hash functions, we develop a deep neural network to learn binary descriptors in an unsupervised manner.  ...  Locality Sensitive Hashing (LSH) [2] applies random projections to map original data into a low-dimensional feature space, and then performs a binarization.  ... 
doi:10.1109/cvpr.2016.133 dblp:conf/cvpr/LinLCZ16 fatcat:2mmikjjpkjdxtfniyyuvwo6ylq
« Previous Showing results 1 — 15 out of 11,285 results