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

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The aim of this paper is to address recognition of natural human actions in diverse and realistic video settings. This challenging but important subject has mostly been ignored in the past due to several problems one of which is the lack of realistic and annotated video datasets. Our first contribution is to address this limitation and to investigate the use of movie scripts for automatic annotation of human actions in videos. We evaluate alternative methods for action retrieval from scripts and show benefits of a text-based classifier. Using the retrieved action samples for visual learning, we next turn to the problem of action classification in video. We present a new method for video classification that builds upon and extends several recent ideas including local space-time features, space-time pyramids and multi-channel non-linear SVMs. The method is shown to improve state-of-the-art results on the standard KTH action dataset by achieving 91.8% accuracy. Given the inherent problem of noisy labels in automatic annotation, we particularly investigate and show high tolerance of our method to annotation errors in the training set. We finally apply the method to learning and classifying challenging action classes in movies and show promising results.

/pdf/learning-realistic-human-actions-from-movies-3draj9xusg.pdf

Learning realistic human actions from movies

Describes a pattern classification approach for detecting frontal-view faces via learning a decision boundary. The classification can be achieved either by explicit estimation of density functions of two classes, face and non-face or by direct learning of a classification function (decision boundary). The latter is a more effective approach, when the number of training available examples is small, compared to the dimensionality of image space. The proposed method consists of a implicit modeling of both face and near-face classes using Independent Component Analysis (ICA), and a subsequent classification stage based on the decision boundary estimation using Support Vector Machine (SVM). Multiple nonlinear SVMs are trained for local subspaces, considering the general non-Gaussian and multi-modal characteristic of face space. This parallelization of SVMs reduces computational cost of on-line classification, since the locally trained SVM has small number of support vectors compared to the SVM trained on entire data space. We showed that the proposed algorithm is superior to the simple combination of ICA and SVM, both in accuracy and computational burden.

Learning a decision boundary for face detection

This paper describes a pattern classifier for detecting frontal-view faces via learning a decision boundary. The proposed classifier consists of two major parts for improving classification accuracy: the implicit modeling of both the face and the near-face classes resulting in an extended discriminative feature set, and the subsequent composite Support Vector Machines (SVMs) for speeding up the classification. For the extended discriminative feature set, Principal Component Analysis (PCA) or Independent Component Analysis (ICA) is performed for the face and near-face classes separately. The projections and distances to the two different subspaces are complementary, which significantly enhances classification accuracy of SVM. Multiple nonlinear SVMs are trained for the local facial feature spaces considering the general multi-modal characteristic of the face space. Each component SVM has a simpler boundary than that of a single SVM for the whole face space. The most appropriate component SVM is selected by a gating mechanism based on clustering. The classification by utilizing one of the multiple SVMs guarantees good generalization performance and speeds up face detection. The proposed classifier is finally implemented to work in real-time by cascading a boosting based face detector.

Composite Support Vector Machines with Extended Discriminative Features for Accurate Face Detection

An electronic device comprising: a memory; a display unit; a communication unit; and at least one processor operatively coupled to the memory, the display unit, and the communication unit, configured to: output a light pattern by using one or more pixels that are part of the display unit; receive, via the communication unit, one or more signals that are transmitted by a wearable device in response to the light pattern; identify a screen display area corresponding to the wearable device based on respective positions of the one or more pixels and the one or more signals.

Method and apparatus for displaying content

A camera setting method comprises the following operations of: sensing surrounding environment information through a sensor or a microphone; and changing setup information with respect to at least one photographing module in accordance with the sensed surrounding environment information in an electronic device including the at least one photographing module. Therefore, the method can set photographing quality for each image obtained by at least one lens.

Apparatus And Method For Setting A Camera

PROBLEM TO BE SOLVED: To provide a method for producing an integral type ink-jet printing head using a single photoresist. SOLUTION: After forming a heating element in a predetermined site of the surface of a substrate 110, the substrate 110 is coated with a negative photoresist 120 by a predetermined thickness. Using a first photo mask provided with patterns of an ink chamber 124 and a restrictor 126 of an ink channel, a site for providing the side wall of a channel forming wall member 120a surrounding the ink chamber 124 and the restrictor 126 of the negative photoresist 120 is hardened by excessive exposure. Using a second photo mask provided with a pattern of a nozzle 122, a site for providing the upper wall of the channel forming wall member 120a of the negative photoresist 120 is exposed for hardening by a predetermined thickness. Finally, the site of the negative photoresist 120, which has not been hardened is dissolved by a solvent so as to be eliminated. COPYRIGHT: (C)2003,JPO

Tae-Kyun Kim

Papers

Learning a decision boundary for face detection

Composite Support Vector Machines with Extended Discriminative Features for Accurate Face Detection

Method and apparatus for displaying content

Apparatus And Method For Setting A Camera

Production method for ink-jet printing head