We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

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.

/pdf/photo-realistic-single-image-super-resolution-using-a-2y0438rlmd.pdf

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Blind image quality assessment (BIQA), which needs nothing about the reference image, is greatly desired in the automatic visual signal processing system. However, without the guide of the reference image, BIQA is extremely difficult to be realized. Distortions degrade the visual contents and cause quality degradation during image perception. From the perspective of information theory, distortions decrease the amount of visual information that an image contains. Therefore, we attempt to measure the image quality with its visual entropy degradation. Inspired by the response in the local receptive field of the retina, the local orientation and intensity features are extracted for visual content representation. Next, the joint probability distributions of the two features are calculated for visual entropy estimation. By deducing the joint entropy equation, the joint probability distributions are decoupled and analyzed. Finally, by measuring the degradations on these decoupled distributions, a novel BIQA method is introduced. Experimental results on the publicly available databases demonstrate that the proposed BIQA performs hiahlv consistent with the human perception.

Joint Entropy Degradation Based Blind Image Quality Assessment

State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown high-resolution images; while the latter - popularized by recently developed deep learning techniques - leverage external image prior from some training dataset. It is natural to explore their middle ground and pursue a hybrid image prior capable of achieving the best in both worlds. In this paper, we propose a systematic approach of achieving this goal called Structured Analysis Sparse Coding (SASC). Specifically, a structured sparse prior is learned from extrinsic training data via a deep convolutional neural network (in a similar way to previous learning-based approaches); meantime another structured sparse prior is internally estimated from the input observation image (similar to previous model-based approaches). Two structured sparse priors will then be combined to produce a hybrid prior incorporating the knowledge from both domains. To manage the computational complexity, we have developed a novel framework of implementing hybrid structured sparse coding processes by deep convolutional neural networks. Experimental results show that the proposed hybrid image restoration method performs comparably with and often better than the current state-of-the-art techniques.

Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding

Nodes layout is a critical issue affecting the quality of service of camera networks. The layout aims at adopting the least number of cameras to cover the whole scene with expected observation quality. This is generally formulated as a non-convex optimization problem which is hard to be solved in polynomial time. In this paper, we propose an efficient near-optimal convex solution for layout guaranteeing satisfactory observation quality based on an anisotropic sensing model of camera. We construct the sensing model based on the physical imaging process. This model provides an accurate measurement of observation quality for the directional nonuniform sensing field of cameras. The layout is treated as selecting the best subset of cameras from a redundant initial layout with numerous cameras. Based on this characteristic and the sensing model, we formulate the layout as a sparse l 0 problem which is further relaxed to a convex l 1 minimization. Therefore, the near-optimal layout is efficiently obtained via convex optimization. Simulation results confirm the effectiveness of the proposed approaches.

Observation quality guaranteed layout of camera networks via sparse representation

No-reference (NR) image quality assessment (IQA) technology is greatly required in quality-orientated visual signal processing systems. However, without the guidance of the reference information, it is still a great challenge for NR IQA to perform consistent with the subjective perception. Researches on cognitive neuroscience state that the human visual system (HVS) presents substantially orientation selectivity mechanism, within which the visual structures are extracted in the local receptive fields for scene understanding. Inspired by this mechanism, a set of orientation selectivity based visual patterns are designed. By analyzing the quality degradation on those patterns, a novel visual pattern degradation based NR IQA method is proposed. Experimental results on large databases demonstrate that the proposed method outperforms the existing NR IQA methods.

No-reference image quality assessment with orientation selectivity mechanism

Vehicle detection based on unmanned aerial vehicle (UAV) images is a challenging task. One reason is that the objects are small size, low-resolution, and large scale variations, resulting in weak feature representation. Another reason is the imbalance between positive and negative examples. In this paper, we propose a novel architecture for UAV vehicle detection to solve above problems. In detail, we use anchor-free mechanism to eliminate predefined anchors, which can reduce complicated computation and relieve the imbalance between positive and negative samples. Meanwhile, to enhance the features for vehicles, we design a multi-scale semantic enhancement block (MSEB) and an effective 49-layer backbone which is based on the DetNet59. The proposed network offers appropriate receptive fields that match the small-sized vehicles, and involves precise localization information provided by the contexts with high resolution. The MSEB strengthens discriminative feature representation at various scales, without reducing the spatial resolution of prediction layers. Experiments show that the proposed method achieves the state-of-the-art performance. Particularly, the main part of vehicles, much smaller ones, the accuracy is about 2% higher than other existing methods.

Guangming Shi

Papers

Joint Entropy Degradation Based Blind Image Quality Assessment

Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding

Observation quality guaranteed layout of camera networks via sparse representation

No-reference image quality assessment with orientation selectivity mechanism

A Feature-Enhanced Anchor-Free Network for UAV Vehicle Detection