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

The paper presents a multiple description (MD) video coder based on three-dimensional (3D) transforms. The coder has low computational complexity and high robustness to transmission errors and is targeted to mobile devices. The encoder represents video sequence in a form of coarse sequence approximation (shaper) included in both descriptions and residual sequence (details) split between two descriptions. The shaper is obtained by block-wise pruned 3D-DCT. The residual sequence is coded by 3D-DCT or hybrid 3D-transform. The coding scheme is simple and yet outperforms some MD coders based on motion-compensated prediction, especially in the low-redundancy region.

A low-complexity multiple description video coder based on 3D-transforms

In various practical situations of remote sensing image processing it is assumed that noise is nonstationary and no a
priory information on noise dependence on local mean or about local properties of noise statistics is available. It is
shown that in such situations it is difficult to find a proper filter for effective image processing, i.e., for noise removal
with simultaneous edge/detail preservation. To deal with such images, a local adaptive filter based on discrete cosine
transform in overlapping blocks is proposed. A threshold is set locally based on a noise standard deviation estimate
obtained for each block. Several other operations to improve performance of the locally adaptive filter are proposed and
studied. The designed filter effectiveness is demonstrated for simulated data as well as for real life radar remote sensing
and marine polarimetric radar images.

Local Adaptive Filtering of Images Corrupted by Nonstationary Noise

JPEG compression with recursive group coding.

The problem of pedestrian classification by radars with different operating bands is considered. The proposed solutions are based on two observations of relation between Doppler spectrums collected within different frequency bands. According to the first observation the Doppler spectrum obtained from the radars with lower operating frequency is an approximate scaled version of the Doppler spectrum obtained within radar with higher operating frequency. According to the second observation the Doppler spectrum of lower operating frequency is similar to the Doppler spectrum of higher operating frequency at specific aspect angle. Two new approaches are proposed for pedestrian classification based on the observations. The first proposed approach deals with new features called local binary mask. The second approach is based on higher order spectral invariants estimated from the Doppler spectrum. The approaches are tested on real 24 GHz radar measurements and simulated 77 GHz radar measurements and show the robustness to operating frequency of the radar.

Radar frequency band invariant pedestrian classification

We present a system for 3D visualisation, which combines user-tracking, used by displays with steerable optics, with generation of multiple views, typical for displays with fixed optical filter. Instead of eye-tracking, typical for the user- tracking approach, we propose a less computationally demanding head tracking, based on face detection. We investigate if the precise delivery of different images to each eye of the observer can be handled by the fixed optics of a multiview 3D display, and if continuous head parallax can be achieved.

Karen Egiazarian

Papers

A low-complexity multiple description video coder based on 3D-transforms

Local Adaptive Filtering of Images Corrupted by Nonstationary Noise

JPEG compression with recursive group coding.

Radar frequency band invariant pedestrian classification

Opengl-Based Control of Semi-Active 3D Display