27,830 Hits in 2.8 sec

Super-sparse Learning in Similarity Spaces [article]

Ambra Demontis, Marco Melis, Battista Biggio, Giorgio Fumera, Fabio Roli
2017 arXiv   pre-print
Current reduction approaches select a small subset of representative prototypes in the space induced by the similarity measure, and then separately train the classification function on the reduced subset  ...  In several applications, input samples are more naturally represented in terms of similarities between each other, rather than in terms of feature vectors.  ...  g(x) for our super-sparse learning algorithm (right).  ... 
arXiv:1712.06131v1 fatcat:vgr7a74wnveirneer2dbeuxhki

A Survey on Various Single Image Super Resolution Techniques

A.Haza rathaiah
2013 International Journal of Innovative Research in Science, Engineering and Technology  
Super-resolution from a single frame is play an important role in many computer vision systems.  ...  In this paper, we presented different existing super resolution methods, positive and negative aspects of those methods, relevant work and methods of super resolution reconstruction method.  ...  In paper [3] propose a algorithm for fast single image super resolution based on self-example learning and sparse representation.  ... 
doi:10.15680/ijirset.2012.0102024 fatcat:t45xr2uapvcrdnzds7ldc37eta

Beta Process Joint Dictionary Learning for Coupled Feature Spaces with Application to Single Image Super-Resolution

Li He, Hairong Qi, Russell Zaretzki
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
The proposed algorithm is able to learn sparse representations that correspond to the same dictionary atoms with the same sparsity but different values in coupled feature spaces, thus bringing consistent  ...  We compare the proposed approach to several state-of-the-art dictionary learning methods by applying this method to single image super-resolution.  ...  The intuitive method to learn dictionaries for coupled feature spaces is using single sparse coding model to learn the coupled dictionaries in concatenated spaces [25] .  ... 
doi:10.1109/cvpr.2013.51 dblp:conf/cvpr/HeQZ13 fatcat:vuis3qxxtvbxtp4j5sdk54ck4i

Conformal and Low-Rank Sparse Representation for Image Restoration

Jianwei Li, Xiaowu Chen, Dongqing Zou, Bo Gao, Wei Teng
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
It is expected that preserving data structure during sparse coding and dictionary learning can enhance the recovery performance.  ...  In this paper, we propose a novel sparse representation approach called conformal and low-rank sparse representation (CLRSR) for image restoration problems.  ...  This work is supported in part by grants from NSFC (61325011) & (61421003), 863 Program (2013AA013801), and SRFDP (20131102130002).  ... 
doi:10.1109/iccv.2015.35 dblp:conf/iccv/LiCZGT15 fatcat:43chodi3nfhqbesvymneacx45i

Image Transformation Based on Learning Dictionaries across Image Spaces

Kui Jia, Xiaogang Wang, Xiaoou Tang
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we propose a framework of transforming images from a source image space to a target image space, based on learning coupled dictionaries from a training set of paired images.  ...  For any test image patch, we can fast index into its closest local cluster and perform a local parametric regression between the learned sparse feature spaces.  ...  Spiritually similar, Kim and Kwon [12] adopted sparse kernel ridge regression to learn a mapping function from paired training patches, and applied it to super-resolution.  ... 
doi:10.1109/tpami.2012.95 pmid:22529324 fatcat:b26jvrj4w5g3tpt2ayqpru4nru

Single-Image Super-Resolution Algorithm Based on Structural Self-Similarity and Deformation Block Features

Yuantao Chen, Jin Wang, Xi Chen, Mingwei Zhu, Kai Yang, Zhi Wang, Runlong Xia
2019 IEEE Access  
internal dictionary size is increased by the geometric deformation of the sample block; Finally, in order to improve the anti-noise performance of the reconstructed picture, a group sparse learning dictionary  ...  INDEX TERMS Super-resolution, deformation block features, block matching, dictionary learning.  ...  Therefore, the maximizing method uses the search for a source patch similar to the object patch, and it has a larger scale in the input LR image space.  ... 
doi:10.1109/access.2019.2911892 fatcat:yzafj52vdfdchmv645gxhhia6i

Tensor Super-Resolution with Generative Adversarial Nets: A Large Image Generation Approach [chapter]

Zihan Ding, Xiao-Yang Liu, Miao Yin, Linghe Kong
2019 Communications in Computer and Information Science  
More specifically, we design a tensor super-resolution process that consists of tensor dictionary learning and tensor coefficients learning.  ...  In this paper, we propose a novel scheme using tensor super-resolution with adversarial generative nets (TSRGAN), to generate large high-quality images by exploring tensor structures.  ...  For an input tensor T ∈ R d×N ×n , tensor dictionary learning is similar to (the only difference is the dimensions) the tensor sparse coding in Section 3.2, where D ∈ R d×m×n is the tensor dictionary,  ... 
doi:10.1007/978-981-15-1398-5_15 fatcat:jtt7owp4drdmzfceowda5336ie

Image Super-Resolution Based on Sparse Coding with Multi-Class Dictionaries

Xiuxiu Liao, Kejia Bai, Qian Zhang, Xiping Jia, Shaopeng Liu, Jin Zhan
2019 Computing and informatics  
In this paper, a super-resolution reconstruction algorithm based on sparse coding with multi-class dictionaries is put forward.  ...  Sparse coding-based single image super-resolution has attracted much interest.  ...  Specifically, small image patches in the low and high-resolution images form manifolds with similar local geometry in two distinct feature spaces.  ... 
doi:10.31577/cai_2019_6_1301 fatcat:t33wxsnnwfbujlrl6mbmtyfqvm

Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Radu Timofte, Vincent De, Luc Van Gool
2013 2013 IEEE International Conference on Computer Vision  
This paper proposes fast super-resolution methods while making no compromise on quality. First, we support the use of sparse learned dictionaries in combination with neighbor embedding methods.  ...  Recently there have been significant advances in image upscaling or image super-resolution based on a dictionary of low and high resolution exemplars.  ...  In the case of the learned sparse dictionaries, we obtain l 2 -normalized atoms meant to form a basis spanning the space of the training samples while minimizing the reconstruction error.  ... 
doi:10.1109/iccv.2013.241 dblp:conf/iccv/TimofteDG13 fatcat:te7gdisdejdovbvcwh46jugdum

Super-Sparse Regression for Fast Age Estimation from Faces at Test Time [chapter]

Ambra Demontis, Battista Biggio, Giorgio Fumera, Fabio Roli
2015 Lecture Notes in Computer Science  
regression in the space induced by the similarity measure.  ...  Given a similarity measure between faces, our technique learns a sparse set of virtual face prototypes, whose number is fixed a priori, along with a set of optimal weight coefficients to perform linear  ...  This approach is clearly linear in the space induced by the similarity function, but not necessarily in the input space X , i.e., the similarity mapping can be used to induce nonlinearity as in kernel  ... 
doi:10.1007/978-3-319-23234-8_51 fatcat:wuwlhnpxxnh4bclwatggzurfoa

Single color image super-resolution using sparse representation and color constraint

Zhigang Xu, Qiang Ma, Feixiang Yuan
2020 Journal of Systems Engineering and Electronics  
Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm (e.g., L 1 or L 2 ).  ...  This paper presents a color super-resolution reconstruction method combining the L 2/3 sparse regularization model with color channel constraints.  ...  This problem can be mitigated by adding strong prior information to the solution space. To learn the prior, the learning-based strategies for SR have got a lot of attention in recent years [3, 4] .  ... 
doi:10.23919/jsee.2020.000004 fatcat:f5af7vful5bd7irg7m3xcqxec4

Face Recognition in Low Quality Images: A Survey [article]

Pei Li, Loreto Prieto, Domingo Mery, Patrick Flynn
2019 arXiv   pre-print
Several studies addressed this problem employed techniques like super resolution, deblurring, or learning a relationship between different resolution domains.  ...  Faces in these images are generally small in size.  ...  the similarity of the face in HR face space, thus serious artifacts were involved.  ... 
arXiv:1805.11519v3 fatcat:izpl554u3fga5d62e6jxw4zuwu

Single Image Super-Resolution - A Quantitative Comparison

Lisha P P, Jayasree V K
2015 International Journal of Engineering Research and  
From the analysis we have found that learning based algorithm using sparse dictionary performs better.  ...  This paper presents a comparison on well-known techniques of super resolution.  ...  Spatial or pixel resolution is defined as spacing of pixels in an image and it is measured in terms of number of column pixels with number of row pixels.  ... 
doi:10.17577/ijertv4is050888 fatcat:65vgcn5xkzckxdbqbozfsqv6ma

How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS [article]

Kaicheng Yu and Rene Ranftl and Mathieu Salzmann
2020 arXiv   pre-print
Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the super-net.  ...  Our analysis uncovers that some commonly-used heuristics for super-net training negatively impact the correlation between super-net and stand-alone performance, and evidences the strong influence of certain  ...  For NASBench-101, we can see that learning rates of 0.025 and 0.05 clearly outperform other learning rates in terms of sparse Kendall-Tau and validation accuracy.  ... 
arXiv:2003.04276v2 fatcat:nvrmqiwu2bg4pe7l3kbxu6b2sa

TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation [article]

Zihan Ding, Xiao-Yang Liu, Miao Yin, Linghe Kong
2019 arXiv   pre-print
More specifically, we design a tensor super-resolution process that consists of tensor dictionary learning and tensor coefficients learning.  ...  Essentially, the adversarial process of TGAN takes place in a tensor space.  ...  For an input tensor T ∈ R d×N ×n , tensor dictionary learning is similar to (the only difference is the dimensions) the tensor sparse coding in Section 3.2, where D ∈ R d×m×n is the tensor dictionary,  ... 
arXiv:1901.09953v2 fatcat:qxecq5meorhotpcpaamnt2n5ha
« Previous Showing results 1 — 15 out of 27,830 results