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

Human hand has amazing super-resolution ability in sensing the force and position of contact and this ability can be strengthened by practice. Inspired by this, we propose a method for robotic tactile super-resolution enhancement by learning spatiotemporal continuity of contact position and a tactile sensor composed of overlapping air chambers. Each overlapping air chamber is constructed of soft material and seals the barometer inside to mimic adapting receptors of human skin. Each barometer obtains the global receptive field of the contact surface with the pressure propagation in the hyperelastic seal overlapping air chambers. 
Neural networks with causal convolution are employed to resolve the pressure data sampled by barometers and to predict the contact position. The temporal consistency of spatial position contributes to the accuracy and stability of positioning. We obtain an average super-resolution (SR) factor of over 2500 with only four physical sensing nodes on the rubber surface (0.1 mm in the best case on 38 × 26 mm²), which outperforms the state-of-the-art. The effect of time series length on the location prediction accuracy of causal convolution is quantitatively analyzed in this article. 
We show that robots can accomplish challenging tasks such as haptic trajectory following, adaptive grasping, and human-robot interaction with the tactile sensor. This research provides new insight into tactile super-resolution sensing and could be beneficial to various applications in the robotics field.

https://ojs.aaai.org/index.php/AAAI/article/download/25763/25535

Improving Robotic Tactile Localization Super-resolution via Spatiotemporal Continuity Learning and Overlapping Air Chambers

With the rapid development of remote sensing sensor technology, the number of remote sensing images (RSIs) has exploded. How to effectively retrieve and manage this massive data have become an urgent problem. At present, content-based image retrieval (CBIR) methods have become a mainstream method due to their excellent performance. However, most of the existing retrieval methods only consider the global features of images, which lacks the ability to discriminate images with the same semantic information but different visual representations. To alleviate this issue, supervised contrastive learning based on the fusion of global and local features method is proposed in this article, named SCFR. First, a fusion module is designed to combine global and local features to enhance the ability of image expression. Second, supervised contrastive learning is introduced into the retrieval task to effectively improve the feature distribution, so that the positive sample pairs are close to each other, and the negative sample pairs are far away from each other in the feature space. Furthermore, to make the distribution of features of the same class more compact, the center contrastive loss is added to the constraints and combines the class centers that change iteratively with the network. Experimental results on three RSI datasets show that our proposed method has a more effective retrieval performance than the state-of-the-art methods. The code and models are available at https://github.com/xdplay17/SCFR.

Supervised Contrastive Learning Based on Fusion of Global and Local Features for Remote Sensing Image Retrieval

Deep neural networks have been applied to video compressive sensing (VCS) task recently. The existing DNN-based VCS methods compress and reconstruct the scene video only in space or time dimensions, which ignores the spatial-temporal correlation of the video. And they generally utilize pixel-wise loss as the loss function, which causes the results to be over-smoothed. In this paper, we propose a perceptual spatial-temporal VCS network. The spatial-temporal VCS network, which compresses and recovers the video in both space and time dimensions, can preserve the spatial-temporal correlation of the video. Besides, we refine the perceptual loss by selecting specific feature-wise loss terms and adding a pixel-wise loss term. The refined perceptual loss can guide the spatial-temporal network to retain more textures and structures. Experimental results show the proposed method can achieve better visual effect with less recovery time than the state-of-the-art.

Perceptual spatial-temporal video compressive sensing network

It is well-known that the sparse representation (SR) based ISAR imaging schemes suffer from high cost on memory and computation complexity, because the two-dimensional imaging observation procedure is jointly represented by a large-scale basis matrix. To overcome this difficulty, a novel separable SR-based ISAR imaging algorithm is developed in this paper. By introducing a separable observation model, the large-scale basis is replaced by two small-scale bases, which brings significant reduction on memory and complexity. To efficiently solve the imaging problem, the range profile is engaged as an auxiliary variable, and the sparsity on both the scene and the range profile is exploited, by which the scene can be reconstructed in matrix operation directly instead of the memory consuming vector operations. Compared with the traditional SR-based imaging scheme, the memory cost for storing the basis matrix can be dropped from MN×PQ to MP+QN, and the computation complexity is reduced from O(P3 Q3) to O(P3+Q3), where M, P and N, Q stand for the numbers of samples and grids in range and cross-range directions. The superior performance of the proposed algorithm is proved by simulated data and real data.

ISAR imaging with separable sparse representation model

Stack filters are often employed for suppressing the pulse noise. In general, the larger sizes the stack filters are, the better results are. Unfortunately, available algorithms for designing stack filters can only be suit for small window sizes due to their huge computational complexities. This paper presents a new fast adaptive algorithm for designing a stack filter with large windows. The idea of the new algorithm is to divide a lager window into many sub-windows. The procedures of dividing a large window are given. An Immune Memory Clonal Selection Algorithm is employed to design the stack filters with small window sizes. Because of its highly parallel structure, it can be very fast implemented. As an experiment, the algorithm was used to restore images corrupted by uncorrelated additive noise with the level from 10% to 50 %. The results show that the algorithm is effective and feasible.

Guangming Shi

Papers

Improving Robotic Tactile Localization Super-resolution via Spatiotemporal Continuity Learning and Overlapping Air Chambers

Supervised Contrastive Learning Based on Fusion of Global and Local Features for Remote Sensing Image Retrieval

Perceptual spatial-temporal video compressive sensing network

ISAR imaging with separable sparse representation model

A new fast algorithm for training large window stack filters