Filters








36,778 Hits in 6.5 sec

Transfer Learning Based on A+ for Image Super-Resolution [chapter]

Mei Su, Sheng-hua Zhong, Jian-min Jiang
2016 Lecture Notes in Computer Science  
Therefore, in this paper, a new algorithm Transfer Learning based on A+ (TLA) is proposed for image super-resolution task.  ...  Example learning-based super-resolution (SR) methods are effective to generate a high-resolution (HR) image from a single low-resolution (LR) input.  ...  Therefore, the transfer learning based on face images is beneficial to the performance of super-resolution task.  ... 
doi:10.1007/978-3-319-47650-6_26 fatcat:pnmziyjymvan5dm7dabisvdasm

Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attacks [article]

Jun-Ho Choi, Huan Zhang, Jun-Hyuk Kim, Cho-Jui Hsieh, Jong-Seok Lee
2019 arXiv   pre-print
Single-image super-resolution aims to generate a high-resolution version of a low-resolution image, which serves as an essential component in many computer vision applications.  ...  This paper investigates the robustness of deep learning-based super-resolution methods against adversarial attacks, which can significantly deteriorate the super-resolved images without noticeable distortion  ...  Figure 4 Figure 5 .Figure 6 . 456 summarizes the transferability for the deep learning-based super-resolution models on the BSD100 dataset, where α = 8/255.  ... 
arXiv:1904.06097v2 fatcat:672d2r2mmzdvtf55iynepz7yde

Small Object Detection from Remote Sensing Images with the Help of Object-Focused Super-Resolution Using Wasserstein GANs

Luc Courtrai, Minh-Tan Pham, Chloe Friguet, Sebastien Lefevre
2020 IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium  
Results showed that object-focused super-resolution improves the detection performance and facilitates the transfer learning from one data set to another.  ...  The learning of our super-resolution network is performed using deep residual blocks integrated in a Wasserstein Generative adversarial network.  ...  TRANSFER LEARNING In this section, we show that object-focused super-resolution could be useful within a transfer learning context.  ... 
doi:10.1109/igarss39084.2020.9323236 fatcat:b456ubp7hffk5mcw2oseux5beq

Meta-Transfer Learning for Zero-Shot Super-Resolution

Jae Woong Soh, Sunwoo Cho, Nam Ik Cho
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR.  ...  Precisely, it is based on finding a generic initial parameter that is suitable for internal learning.  ...  Then, meta-transfer learning learns a good representation θ M for super-resolution tasks with diverse blur kernel scenarios. The figure shows N tasks for simplicity.  ... 
doi:10.1109/cvpr42600.2020.00357 dblp:conf/cvpr/SohCC20 fatcat:xqqzijd545gxxg6rcty5ttchpa

Towards Domain Adaptive Vehicle Detection in Satellite Image by Supervised Super-Resolution Transfer

Liujuan Cao, Rongrong Ji, Cheng Wang, Jonathan Li
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
learning to the high-resolution aerial image domain,where rich supervision exists and robust detectors can be trained.To this end, we first propose a super-resolution algorithm using coupled dictionary  ...  of satellite images, as well as the limited training data.In this paper, a robust domain-adaptive vehicle detection framework is proposed to bypass both problems.Our innovation is to transfer the detector  ...  (Kim and Kwon 2010) presented a spare regression based algorithm that adopts ridge regression for super-resolution of a single-frame image.  ... 
doi:10.1609/aaai.v30i1.10166 fatcat:siggikpu2rh2zo3cl7dngex56a

Generative Adversarial Networks for Image Super-Resolution: A Survey [article]

Chunwei Tian, Xuanyu Zhang, Jerry Chun-Wen Lin, Wangmeng Zuo, Yanning Zhang
2022 arXiv   pre-print
Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised  ...  Single image super-resolution (SISR) has played an important role in the field of image processing.  ...  machine learning methods on image super-resolution [21] .  ... 
arXiv:2204.13620v1 fatcat:hlwdqith65cxrbqrnbphjz6u4u

Meta-Transfer Learning for Zero-Shot Super-Resolution [article]

Jae Woong Soh, Sunwoo Cho, Nam Ik Cho
2020 arXiv   pre-print
In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR.  ...  Precisely, it is based on finding a generic initial parameter that is suitable for internal learning.  ...  Then, meta-transfer learning learns a good representation θ M for super-resolution tasks with diverse blur kernel scenarios. The figure shows N tasks for simplicity.  ... 
arXiv:2002.12213v1 fatcat:23yd4dwgtjcxnnkgmquav2bd4i

Adversarial Images Against Super-Resolution Convolutional Neural Networks for Free

Arezoo Rajabi, Mahdieh Abbasi, Rakesh B. Bobba, Kimia Tajik
2022 Proceedings on Privacy Enhancing Technologies  
Neural Networks (CNNs)-based image classifiers.  ...  Super-Resolution Convolutional Neural Networks (SRCNNs) with their ability to generate highresolution images from low-resolution counterparts, exacerbate the privacy concerns emerging from automated Convolutional  ...  Acknowledgements This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.  ... 
doi:10.56553/popets-2022-0065 fatcat:aew2plqqdvc4hlfgj37yc4vlsm

A Generative Adversarial Network for AI-Aided Chair Design

Zhibo Liu, Feng Gao, Yizhou Wang
2019 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)  
It consists of an image synthesis module, which learns the underlying distribution of training dataset, a super-resolution module, which improve quality of generated image and human involvements.  ...  Finally, we manually pick one of the generated candidates to create a real life chair for illustration.  ...  Image to Image Translation Image to Image translation methods have been successfully applied for style transfer and image super-resolution, which can be used as a powerful tool for auxiliary design.For  ... 
doi:10.1109/mipr.2019.00098 dblp:conf/mipr/LiuGW19 fatcat:wc5ijncuynhhxgt3an5n2e5vs4

Reference based Face Super-resolution

Zhi-Song Liu, Wan-Chi Siu, Yui-Lam Chan
2019 IEEE Access  
We create a benchmark dataset on reference based face super-resolution (RefSR-Face) for general research use, which contains reference images paired with low-resolution images of various pose, emotions  ...  We propose a novel Conditional Variational AutoEncoder model for this Reference based Face Super-Resolution (RefSR-VAE).  ...  The neural style transfer is built based on a feed-forward network to transfer the style of the reference image to the input LR image to aid the super-resolution process.  ... 
doi:10.1109/access.2019.2934078 fatcat:qw6mh56ysvfpjbvno4hxn7sgwq

Image Super-resolution Using Mid-level Representations

Li Yang, Yaxing Wang, Xiaomin Mu, Yaping Wang
2016 DEStech Transactions on Engineering and Technology Research  
An end-to-end six layers convolutional neural network(CNNs) structure is proposed to realize single image super-resolution reconstruction.  ...  The input of the network is low-resolution (LR) image, and the output is the superresolution (SR) image. Promising experimental results are obtained with higher precision.  ...  Sparse coding (SC) is a representative learning-based method for single image super-resolution reconstruction [4] .  ... 
doi:10.12783/dtetr/iect2016/3750 fatcat:7aqy4lax5bgj7i5v5b3frv6zsi

Fast Image Super-Resolution Based on In-Place Example Regression

Jianchao Yang, Zhe Lin, Scott Cohen
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a fast regression model for practical single image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approacheslearning from an external database and  ...  Based on the in-place examples, a first-order approximation of the nonlinear mapping function from low-to high-resolution image patches is learned.  ...  We propose a new fast super-resolution algorithm based on regression on in-place examples, which, for the first time, leverages the two fundamental super-resolution approaches of learning from externalexamples  ... 
doi:10.1109/cvpr.2013.141 dblp:conf/cvpr/YangLC13 fatcat:z4cbctbvmvhrtldah2i6rstvq4

A New Makeup Transfer with Super-resolution

Yeqing Ren, Youqiang Sun, Di Wu, Zhihua Cui, Alex Kai Qin
2019 Australian Journal of Intelligent Information Processing Systems  
With the wide use of beauty camera, the makeup transfer for old photo has a certain application value.  ...  In this paper, we propose a new makeup transfer model considering a specific scene that is blurry target image.  ...  (a) A blurry target image; (b) Example image for makeup transfer. Fig. 6 : 6 Fig. 6: The improvement of makeup transfer by super-resolution method.  ... 
dblp:journals/ajiips/RenSWCQ19 fatcat:rrgaioa2bjhkzm373vu37hzptu

A Comparable Study of CNN-Based Single Image Super-Resolution for Space-Based Imaging Sensors

Haopeng Zhang, Pengrui Wang, Cong Zhang, Zhiguo Jiang
2019 Sensors  
In this paper, we comparably study four recent popular models for single image super-resolution based on convolutional neural networks (CNNs) with the purpose of space applications.  ...  We specially fine-tune the super-resolution models designed for natural images using simulated images of space objects, and test the performance of different CNN-based models in different conditions that  ...  (Very Deep Super-resolution Convolutional Networks), and DRCN [43] (Deeply-Recursive Convolutional Networks) for single image super-resolution based on CNNs.  ... 
doi:10.3390/s19143234 fatcat:7kypbe2zmreqxdfduceodzggda

Anchored neighborhood deep network for single-image super-resolution

Wuzhen Shi, Shaohui Liu, Feng Jiang, Debin Zhao, Zhihong Tian
2018 EURASIP Journal on Image and Video Processing  
In this paper, we establish the relationship between the traditional sparse-representation-based single-image super-resolution methods and the deep-learning-based ones and use transfer learning to make  ...  Therefore, how to make full use of image prior is one of the unsolved problems for deep-network-based single image super-resolution methods.  ...  Acknowledgements We would like to acknowledge all our team members, especially Min Gao and Xinwei Gao, for their constructive suggestions on deep-learning-based image restoration and image compression.  ... 
doi:10.1186/s13640-018-0269-7 fatcat:spvm2uk5mjbetiurebb54gp7fy
« Previous Showing results 1 — 15 out of 36,778 results