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

Within the long-time coherent integration (CI) in radar detection, the range walk effect inevitably impacts high-speed targets, which makes coherent detection methods invalid. To address this problem, a coherent detection method, a modified radon inverse Fourier transform (MRIFT), was developed in this article. The MRIFT can estimate velocity via single parameter searching and achieve the target's CI in the 2-D frequency domain using the inverse Fourier transform. Compared with the traditional coherent detection methods, the MRIFT achieved great detection performance and range and velocity estimation performance and averted the blind speed side lobe effect at a lower computational cost. Simulations demonstrate the effectiveness and efficiency of the proposed MRIFT.

Radar High-Speed Target Coherent Detection Method Based on Modified Radon Inverse Fourier Transform

Both network pruning and neural architecture search (NAS) can be interpreted as techniques to automate the design and optimization of artificial neural networks. In this paper, we challenge the conventional wisdom of training before pruning by proposing a joint search-and-training approach to learn a compact network directly from scratch. Using pruning as a search strategy, we advocate three new insights for network engineering: 1) to formulate adaptive search as a cold start strategy to find a compact subnetwork on the coarse scale; and 2) to automatically learn the threshold for network pruning; 3) to offer flexibility to choose between efficiency and robustness. More specifically, we propose an adaptive search algorithm in the cold start by exploiting the randomness and flexibility of filter pruning. The weights associated with the network filters will be updated by ThreshNet, a flexible coarse-to-fine pruning method inspired by reinforcement learning. In addition, we introduce a robust pruning strategy leveraging the technique of knowledge distillation through a teacher-student network. Extensive experiments on ResNet and VGGNet have shown that our proposed method can achieve a better balance in terms of efficiency and accuracy and notable advantages over current state-of-the-art pruning methods in several popular datasets, including CIFAR10, CIFAR100, and ImageNet. The code associate with this paper is available at: https://see.xidian.edu.cn/faculty/wsdong/Projects/AST-NP.htm.

Adaptive Search-and-Training for Robust and Efficient Network Pruning

With the development of remote sensing technology, the earth observation data shows a blowout growth. How to quickly and accurately retrieve the target content from the massive data has become a noteworthy task. Recently, the methods based on convolutional neural networks (CNN) have been far ahead in remote sensing retrieval. However, due to the diversity of sources acquired, remote sensing images with the same semantic information may have great visual differences. The pre-trained CNN is not always able to successfully extract representative and distinguishing features to recognize the target content. To address this problem, a supervised contrastive learning-based deep hash retrieval method (SCLDHR) is introduced in this paper, which effectively uses label information to gather image features belonging to the same class and separate image features of different classes in the embedding space. Furthermore, a quantization function in the hash space is designed to improve hashing quality. The experimental results conducted on three datasets show that SCLDHR can achieve competitive retrieval performance compared with state-of-the-art methods.

Supervised Contrastive Learning-Based Deep Hash Retrieval for Remote Sensing Image

For inter frame coding, the motion-compensated residual takes a large proportion of the total bits and the efficiency of the followed transform greatly affects the compression performance. In this paper, we propose an adaptive transform scheme to further exploit the non-local correlation for the motion-compensated residual. For a video sequence, there are usually repeating similar contents, especially between adjacent frames, known as temporal redundancy. We then use these content-similar blocks of the coding block, which most probably reflect the characteristic of the coding block, to train the adaptive transform. The predicted block together with the boundary reconstructed pixels of the coding block forms the target patch and is used to guide the searching of similar blocks. By fully exploring the correlation of abundant similar blocks, the proposed scheme achieves 0.1~0.5 dB gain in term of PSNR at high bit rate over the state-of-the-art scheme. For Mobile and BQSquare, 1dB gain is obtained at high bit rate.

Inter frame coding with adaptive transform

This paper studies a multi-Intelligent Reflecting Surfaces (IRSs)-assisted wireless network consisting of multiple base stations (BSs) serving a set of mobile users. We focus on the IRS-BS association problem in which multiple BSs compete with each other for controlling the phase shifts of a limited number of IRSs to maximize the long-term downlink data rate for the associated users. We propose MDLBI, a Multi-agent Deep Reinforcement Learning-based BS-IRS association scheme that optimizes the BS-IRS association as well as the phase-shift of each IRS when being associated with different BSs. MDLBI does not require information exchanging among BSs. Simulation results show that MDLBI achieves significant performance improvement and is scalable for large networking systems.

Guangming Shi

Papers

Radar High-Speed Target Coherent Detection Method Based on Modified Radon Inverse Fourier Transform

Adaptive Search-and-Training for Robust and Efficient Network Pruning

Supervised Contrastive Learning-Based Deep Hash Retrieval for Remote Sensing Image

Inter frame coding with adaptive transform

Optimizing Intelligent Reflecting Surface-Base Station Association for Mobile Networks