Going Much Wider with Deep Networks for Image Super-Resolution
01 Mar 2020-pp 2343-2354
TL;DR: This work proposes a divide and conquer approach based wide and deep network (WDN) that divides the 4× up-sampling problem into 32 disjoint subproblems that can be solved simultaneously and independently of each other.
Abstract: Divide and Conquer is a well-established approach in the literature that has efficiently solved a variety of problems. However, it is yet to be explored in full in solving image super-resolution. To predict a sharp up-sampled image, this work proposes a divide and conquer approach based wide and deep network (WDN) that divides the 4× up-sampling problem into 32 disjoint subproblems that can be solved simultaneously and independently of each other Half of these subproblems deal with predicting the overall features of the high-resolution image, while the remaining are exclusively for predicting the finer details. Additionally, a technique that is found to be more effective in calibrating the pixel intensities has been proposed. Results obtained on multiple datasets demonstrate the improved performance of the proposed wide and deep network over state-of-the-art methods.
Citations
More filters
TL;DR: The benefit of JDSR to high-quality image reconstruction from real-world Bayer pattern data collected by NASA Mars Curiosity is verified and its practical significance in computational imaging is demonstrated.
Abstract: Image demosaicing and super-resolution are two important tasks in color imaging pipeline. So far they have been mostly independently studied in the open literature of deep learning; little is known about the potential benefit of formulating a joint demosaicing and super-resolution (JDSR) problem. In this article, we propose an end-to-end optimization solution to the JDSR problem and demonstrate its practical significance in computational imaging. Our technical contributions are mainly two-fold. On network design, we have developed a Residual-Dense Squeeze-and-Excitation Networks (RDSEN) supported by a pre-demosaicing network (PDNet) as the pre-processing step. We address the issue of spatio-spectral attention for color-filter-array (CFA) data and discuss how to achieve better information flow by concatenating Residue-Dense Squeeze-and-Excitation Blocks (RDSEBs) for JDSR. Experimental results have shown that significant PSNR/SSIM gain can be achieved by RDSEN over previous network architectures including state-of-the-art RCAN. On perceptual optimization, we propose to leverage the latest ideas including relativistic discriminator and pre-excitation perceptual loss function to further improve the visual quality of textured regions in reconstructed images. Our extensive experiment results have shown that Texture-enhanced Relativistic average Generative Adversarial Network (TRaGAN) can produce both subjectively more pleasant images and objectively lower perceptual distortion scores than standard GAN for JDSR. Finally, we have verified the benefit of JDSR to high-quality image reconstruction from real-world Bayer pattern data collected by NASA Mars Curiosity.
17 citations
Cites background from "Going Much Wider with Deep Networks..."
...EDSR [25] proposed to integrate several resblocks and remove batch-normalization layer, which can save GPU memory, stack more layers and make networks wider [38], to further improve SISR performance....
[...]
...We have experimentally verified that such design of deeper and wider networks [38] based on concatenation of multiple RDSEB modules indeed helps the boosting of our JDSR performance....
[...]
TL;DR: A multi-stage neural network architecture ‘HFR-Net’ is proposed that works on the principle of ‘explicit refinement and fusion of high-frequency details’ that gives better results than the current state-of-the-art techniques.
9 citations
Posted Content•
TL;DR: This work proposes an approach to divide the problem of image super-resolution into multiple subproblems and then solve/conquer them with the help of a neural network, and designs an alternate network architecture that is much wider than existing networks and is specially designed to implement the divide-and-conquer design paradigm with a Neural Network.
Abstract: Divide and conquer is an established algorithm design paradigm that has proven itself to solve a variety of problems efficiently. However, it is yet to be fully explored in solving problems with a neural network, particularly the problem of image super-resolution. In this work, we propose an approach to divide the problem of image super-resolution into multiple sub-problems and then solve/conquer them with the help of a neural network. Unlike a typical deep neural network, we design an alternate network architecture that is much wider (along with being deeper) than existing networks and is specially designed to implement the divide-and-conquer design paradigm with a neural network. Additionally, a technique to calibrate the intensities of feature map pixels is being introduced. Extensive experimentation on five datasets reveals that our approach towards the problem and the proposed architecture generate better and sharper results than current state-of-the-art methods.
4 citations
Cites background from "Going Much Wider with Deep Networks..."
...Before proceeding ahead, we mention that this work is an expansion of our prior1 work [4]....
[...]
TL;DR: Zhang et al. as discussed by the authors proposed an approach to divide the problem of image super-resolution into multiple subproblems and then solve/conquer them with the help of a neural network.
Abstract: Divide and conquer is an established algorithm design paradigm that has proven itself to solve a variety of problems efficiently. However, it is yet to be fully explored in solving problems with a neural network, particularly the problem of image super-resolution. In this work, we propose an approach to divide the problem of image super-resolution into multiple subproblems and then solve/conquer them with the help of a neural network. Unlike a typical deep neural network, we design an alternate network architecture that is much wider (along with being deeper) than existing networks and is specially designed to implement the divide-and-conquer design paradigm with a neural network. Additionally, a technique to calibrate the intensities of feature map pixels is being introduced. Extensive experimentation on five datasets reveals that our approach towards the problem and the proposed architecture generate better and sharper results than current state-of-the-art methods.
1 citations
References
More filters
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Abstract: Objective methods for assessing perceptual image quality traditionally attempted to quantify the visibility of errors (differences) between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative complementary framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a structural similarity index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. A MATLAB implementation of the proposed algorithm is available online at http://www.cns.nyu.edu//spl sim/lcv/ssim/.
40,609 citations
Proceedings Article•
31 Mar 2010TL;DR: The objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future.
Abstract: Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with experimental results showing the superiority of deeper vs less deep architectures. All these experimental results were obtained with new initialization or training mechanisms. Our objective here is to understand better why standard gradient descent from random initialization is doing so poorly with deep neural networks, to better understand these recent relative successes and help design better algorithms in the future. We first observe the influence of the non-linear activations functions. We find that the logistic sigmoid activation is unsuited for deep networks with random initialization because of its mean value, which can drive especially the top hidden layer into saturation. Surprisingly, we find that saturated units can move out of saturation by themselves, albeit slowly, and explaining the plateaus sometimes seen when training neural networks. We find that a new non-linearity that saturates less can often be beneficial. Finally, we study how activations and gradients vary across layers and during training, with the idea that training may be more difficult when the singular values of the Jacobian associated with each layer are far from 1. Based on these considerations, we propose a new initialization scheme that brings substantially faster convergence. 1 Deep Neural Networks Deep learning methods aim at learning feature hierarchies with features from higher levels of the hierarchy formed by the composition of lower level features. They include Appearing in Proceedings of the 13 International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, Chia Laguna Resort, Sardinia, Italy. Volume 9 of JMLR: WC Weston et al., 2008). Much attention has recently been devoted to them (see (Bengio, 2009) for a review), because of their theoretical appeal, inspiration from biology and human cognition, and because of empirical success in vision (Ranzato et al., 2007; Larochelle et al., 2007; Vincent et al., 2008) and natural language processing (NLP) (Collobert & Weston, 2008; Mnih & Hinton, 2009). Theoretical results reviewed and discussed by Bengio (2009), suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g. in vision, language, and other AI-level tasks), one may need deep architectures. Most of the recent experimental results with deep architecture are obtained with models that can be turned into deep supervised neural networks, but with initialization or training schemes different from the classical feedforward neural networks (Rumelhart et al., 1986). Why are these new algorithms working so much better than the standard random initialization and gradient-based optimization of a supervised training criterion? Part of the answer may be found in recent analyses of the effect of unsupervised pretraining (Erhan et al., 2009), showing that it acts as a regularizer that initializes the parameters in a “better” basin of attraction of the optimization procedure, corresponding to an apparent local minimum associated with better generalization. But earlier work (Bengio et al., 2007) had shown that even a purely supervised but greedy layer-wise procedure would give better results. So here instead of focusing on what unsupervised pre-training or semi-supervised criteria bring to deep architectures, we focus on analyzing what may be going wrong with good old (but deep) multilayer neural networks. Our analysis is driven by investigative experiments to monitor activations (watching for saturation of hidden units) and gradients, across layers and across training iterations. We also evaluate the effects on these of choices of activation function (with the idea that it might affect saturation) and initialization procedure (since unsupervised pretraining is a particular form of initialization and it has a drastic impact).
9,500 citations
"Going Much Wider with Deep Networks..." refers methods in this paper
...All the trainable weights of the model are initialised with Glorot initialisation [18] and tuned with Adam Optimiser having β1 = 0....
[...]
21 Jul 2017
TL;DR: SRGAN as mentioned in this paper proposes a perceptual loss function which consists of an adversarial loss and a content loss, which pushes the solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
Abstract: Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.
6,884 citations
08 Oct 2016
TL;DR: In this paper, the authors combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image style transfer, where a feedforward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.
Abstract: We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing perceptual loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results.
6,639 citations