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

Provided is an MIM capacitor. The MIM capacitor includes a bottom electrode, a dielectric layer which is formed on the bottom electrode, and a top electrode which is formed on the dielectric layer. The top electrode includes a first electrode which includes a first material with a first concentration, a second electrode which includes the first material with a second concentration, and a third electrode which includes the first material with a third concentration.

MIM capacitor and method for fabricating the same, semiconductor device comprising the same

An unmanned aerial vehicle is provided, which includes an aerial vehicle body; a camera mounted on the body; a sensor module installed in the body to sense surrounding environment information; a radio communication module installed in the body to perform radio communication with another communication device; at least one processor installed in the body and electrically connected to the camera, the sensor module, and the radio communication module; and a memory electrically connected to the processor, wherein the memory, during flying of the unmanned aerial vehicle, stores instructions to cause the processor : - to recognize a user's throwing gesture using the unmanned aerial vehicle, - to determine a user direction based on a first motion vector generated by the throwing gesture, - to predict a camera direction in a standstill location that is a target point of the unmanned aerial vehicle based on the throwing gesture, and - to control a photographing direction of the camera

Unmanned aerial vehicle and method for photographing operator using same

We propose a framework that can deform an object in a 2D image as it exists in 3D space. Most existing methods for 3D-aware image manipulation are limited to (1) only changing the global scene information or depth, or (2) manipulating an object of specific categories. In this paper, we present a 3D-aware image deformation method with minimal restrictions on shape category and deformation type. While our framework leverages 2D-to-3D reconstruction, we argue that reconstruction is not sufficient for realistic deformations due to the vulnerability to topological errors. Thus, we propose to take a supervised learning-based approach to predict the shape Laplacian of the underlying volume of a 3D reconstruction represented as a point cloud. Given the deformation energy calculated using the predicted shape Laplacian and user-defined deformation handles (e.g., keypoints), we obtain bounded biharmonic weights to model plausible handle-based image deformation. In the experiments, we present our results of deforming 2D character and clothed human images. We also quantitatively show that our approach can produce more accurate deformation weights compared to alternative methods (i.e., mesh reconstruction and point cloud Laplacian methods).

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian

A thermal inkjet printhead that includes a substrate, a chamber layer stacked on the substrate, an ink chamber formed in the chamber layer, a heater to heat ink filled in the ink chamber to generate bubbles, and a nozzle layer stacked on the chamber layer, and including a nozzle formed in the nozzle layer, wherein a ratio of the volume of ink ejected through the nozzle with respect to the sum of the volumes of the ink chamber and the nozzle is in the range of approximately 40 to 60%.

Thermal inkjet printhead

Augmenting data in image space (eg. flipping, cropping etc) and activation space (eg. dropout) are being widely used to regularise deep neural networks and have been successfully applied on several computer vision tasks. Unlike previous works, which are mostly focused on doing augmentation in the aforementioned domains, we propose to do augmentation in label space. In this paper, we present a novel method to generate fixed dimensional labels with continuous values for images by exploiting the word2vec representations of the existing categorical labels. We then append these representations with existing categorical labels and train the model. We validated our idea on two challenging face attribute classification data sets viz. CelebA and LFWA. Our extensive experiments show that the augmented labels improve the performance of the competitive deep learning baseline and reduce the need of annotated real data up to 50%, while attaining a performance similar to the state-of-the-art methods.

Tae-Kyun Kim

Papers

MIM capacitor and method for fabricating the same, semiconductor device comprising the same

Unmanned aerial vehicle and method for photographing operator using same

Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian

Thermal inkjet printhead

AugLabel: Exploiting Word Representations to Augment Labels for Face Attribute Classification