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

There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

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

计量经济分析 = Econometric analysis

Overtaking on rural roads often becomes dangerous when oncoming traffic is detected by the driver too late or its speed is underestimated. Recently proposed cooperative overtaking assistance systems, which are based on Vehicular Ad hoc NETworks (VANETs), rely on either real-time video transmission or the exchange of status messages (beacons). In the first case, a video stream captured by a camera installed at the windshield of a vehicle is compressed and broadcast to any vehicles driving behind it, where it is displayed to the driver. In the second case, beacons that include position, speed, and direction are frequently broadcast by all the vehicles to ensure detection of oncoming traffic as early as possible and to issue a warning to the driver whenever needed. In this paper, we demonstrate that the performance of a video-based overtaking assistant can be significantly improved if codec channel adaptation is undertaken by exploiting information from the beacons about any forthcoming increase in the load of the multiple access channel used. The theoretical framework presented describes the basic patterns of such a coupled overtaking assistant and can serve as a useful guideline for the future practical implementation of the system. The benefits of our approach are demonstrated in relation to the practical scenario of H.264/AVC video coding and IEEE 802.11p/Wireless Access in Vehicular Environments (WAVE) intervehicle communication standards.

/pdf/an-overtaking-assistance-system-based-on-joint-beaconing-and-3w6ld7i8nw.pdf

An Overtaking Assistance System Based on Joint Beaconing and Real-Time Video Transmission

The paper attacks absolute phase estimation with a two-step approach: the first step applies an adaptive local denoising scheme to the modulo-2π noisy phase; the second step applies a robust phase unwrapping algorithm to the denoised modulo-2π phase obtained in the first step. The adaptive local modulo-2π phase denoising is a new algorithm based on local polynomial approximations. The zero-order and the first-order approximations of the phase are calculated in sliding windows of varying size. The zero-order approximation is used for pointwise adaptive window size selection, whereas the first-order approximation is used to filter the phase in the obtained windows. For phase unwrapping, we apply the recently introduced robust (in the sense of discontinuity preserving) PUMA unwrapping algorithm [IEEE Trans. Image Process.16, 698 (2007)] to the denoised wrapped phase. Simulations give evidence that the proposed algorithm yields state-of-the-art performance, enabling strong noise attenuation while preserving image details.

/pdf/absolute-phase-estimation-adaptive-local-denoising-and-4xrmd6l1fb.pdf

Absolute phase estimation: adaptive local denoising and global unwrapping

In this paper, we present a new method for measuring the temporal noise in the raw-data of digital imaging sensors [e.g., CMOS and charge-coupled device (CCD)]. The method is specially designed to estimate the variance function which describes the signal-dependent noise found in raw-data. It gives the standard-deviation of the noise as a function of the expectation of the pixel raw-data output value. In contrast with established methods (such as the ISO 15739), our method does not require the use of a specific target or a particular calibration. This is possible due to an automatic segmentation embedded in the data analysis. We show experimental results for the raw-data from two different CMOS sensors of commercial cameraphones.

Noise Measurement for Raw-Data of Digital Imaging Sensors by Automatic Segmentation of Nonuniform Targets

We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlocal denoising based on a nonlocal filter (NLF), exploiting the mutual similarities between groups of patches. CNN models are leveraged with noise levels that progressively decrease at every iteration of our framework, while their output is regularized by a nonlocal prior implicit within the NLF. Unlike complicated neural networks that embed the nonlocality prior within the layers of the network, our framework is modular, and it uses standard pretrained CNNs together with standard nonlocal filters. An instance of the proposed framework, called NN3D, is evaluated over large grayscale image datasets showing state-of-the-art performance.

Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising

In this paper, we present a novel stereoscopic video quality assessment method based on 3D-DCT transform. In our approach, similar blocks from left and right views of stereoscopic video frames are found by block-matching, grouped into 3D stack and then analyzed by 3D-DCT. Comparison between reference and distorted images are made in terms of MSE calculated within the 3D-DCT domain and modified to reflect the contrast sensitive function and luminance masking. We validate our quality assessment method using test videos annotated with results from subjective tests. The results show that the proposed algorithm outperforms current popular metrics over a wide range of distortion levels.

Karen Egiazarian

Papers

An Overtaking Assistance System Based on Joint Beaconing and Real-Time Video Transmission

Absolute phase estimation: adaptive local denoising and global unwrapping

Noise Measurement for Raw-Data of Digital Imaging Sensors by Automatic Segmentation of Nonuniform Targets

Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising

3D-DCT based perceptual quality assessment of stereo video