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

Quazi-optimal Zernike feature selection

One of the main problems of neural network-based no-reference metrics design for image visual quality assessment is small size of image databases with mean opinion scores (MOS). For large networks which can memorize key features of several thousands of images, usage of the databases for metrics training may lead to overlearning. Since data augmentation for image quality assessment is limited by a horizontal image flipping only, the main way to decrease overlearning is to use transfer learning which can significantly speed up training process. In theis paper, we propose a new technique of transfer learning between networks of different architectures using a large set of images without MOS. We implemented the technique for transfer learning between pre-trained KonCept512 metric and a IMQNet metric proposed in this paper. An effectiveness of the transfer learning is estimated in a numerical analysis. It is shown that the trained IMQNet metric provides significantly better correlation with KonCept512 metric (0.89) than other modern metrics. It is also shown that IMQNet pre-trained by the proposed transfer learning shows better correlation with MOS of KonIQ-10k database (0.86) than IMQNet pre-trained using directly the MOS of KonIQ10k (0.73). 

Transfer learning for no-reference image quality metrics using large temporary image sets

Methods and tools for denoising of complex-valued images based on block-matching and high order singular value decomposition.

Optimization of stack filters using sample selection probabilities.

It is a quite common that acquired images are noisy and image filtering is a necessary step to enhance them. Usually image filtering effectiveness is characterized in terms of MSE or PSNR although nowadays it is well understood that these criteria do not always correspond adequately to visual perception of processed images. Recently several new measures of image quality have been proposed. In particular, two metrics, called PSNR-HVS and PSNR-HVS-M, were designed and successfully tested 16,17 . Both take into account different sensitivity of a human eye to spatial frequencies, the latter one also accounts for the masking effects. Using th ese two metrics as well as a traditional PSNR and used by NASA metric DCTune, we have analyzed performance of five different filters (standard mean and median, sigma, Lee and DCT based filters) for a set of test images corrupted by an additive Gaussian noise with a wide set of variance val-ues. It has been shown that there are many situations when PSNR after filtering improves while one or all other metrics manifest image quality decreasing. Most often this happens if noise variance is small and/or an image contains texture. Comparisons show that DCT based filter commonly outperforms other considered filters in the sense of denoised image visual quality. At the same time, the standard mean filter produces worse visual quality of processed images even its scanning window size is 3x3. Keywords : additive noise, image filtering, perceptual quality.

Karen Egiazarian

Papers

Quazi-optimal Zernike feature selection

Transfer learning for no-reference image quality metrics using large temporary image sets

Methods and tools for denoising of complex-valued images based on block-matching and high order singular value decomposition.

Optimization of stack filters using sample selection probabilities.

Image filter effectiveness characterization based on HVS