We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

/pdf/imagenet-classification-with-deep-convolutional-neural-1190x9a6b9.pdf

ImageNet Classification with Deep Convolutional Neural Networks

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

/pdf/imagenet-a-large-scale-hierarchical-image-database-1e8f663s1h.pdf

ImageNet: A large-scale hierarchical image database

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

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%, respectively, which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully connected layers we employed a recently developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

/pdf/imagenet-classification-with-deep-convolutional-neural-3kv7rezkq1.pdf

ImageNet classification with deep convolutional neural networks

The visual world around us can be described as a structured set of objects and their associated relations. An image of a room may be conjured given only the description of the underlying objects and their associated relations. While there has been significant work on designing deep neural networks which may compose individual objects together, less work has been done on composing the individual relations between objects. A principal difficulty is that while the placement of objects is mutually independent, their relations are entangled and dependent on each other. To circumvent this issue, existing works primarily compose relations by utilizing a holistic encoder, in the form of text or graphs. In this work, we instead propose to represent each relation as an unnormalized density (an energy-based model), enabling us to compose separate relations in a factorized manner. We show that such a factorized decomposition allows the model to both generate and edit scenes that have multiple sets of relations more faithfully. We further show that decomposition enables our model to effectively understand the underlying relational scene structure. Project page at: https://composevisualrelations.github.io/.

Learning to Compose Visual Relations.

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of different images, can we discover the generative concepts that represent each image? We present an unsupervised approach to discover generative concepts from a collection of images, disentangling different art styles in paintings, objects, and lighting from kitchen scenes, and discovering image classes given ImageNet images. We show how such generative concepts can accurately represent the content of images, be recombined and composed to generate new artistic and hybrid images, and be further used as a representation for downstream classification tasks.

Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

A method for pose recognition includes storing parameters for configuration of an automated pose recognition system for detection of a pose of a subject represented in a radio frequency input signal. The parameters having been determined by a first process including accepting training data including a number of images including poses of subjects and a corresponding number of radio frequency signals and executing a parameter training procedure to determine the parameters. The parameter training procedure including, receiving features characterizing the poses in each of the images, and determining the parameters that configure the automated pose recognition system to match the features characterizing the poses from the corresponding radio frequency signals.

Pose estimation using radio frequency signals

Since their introduction, ranking SVM models [11] have become a powerful tool for training content-based retrieval systems. All we need for training a model are retrieval examples in the form of triplet constraints, i.e. examples specifying that relative to some query, a database item a should be ranked higher than database item b. These types of constraints could be obtained from feedback of users of the retrieval system. Most previous ranking models learn either a global combination of elementary similarity functions or a combination defined with respect to a single database item. Instead, we propose a "coarse to fine" ranking model where given a query we first compute a distribution over "coarse" classes and then use the linear combination that has been optimized for queries of that class. These coarse classes are hidden and need to be induced by the training algorithm. We propose a latent variable ranking model that induces both the latent classes and the weights of the linear combination for each class from ranking triplets. Our experiments over two large image datasets and a text retrieval dataset show the advantages of our model over learning a global combination as well as a combination for each test point (i.e. transductive setting). Furthermore, compared to the transductive approach our model has a clear computational advantages since it does not need to be retrained for each test query.

/pdf/a-latent-variable-ranking-model-for-content-based-retrieval-3j0l2ihrwo.pdf

A latent variable ranking model for content-based retrieval

Internet of things (IoT) has been employed in recent years across multiple disciplines in the Fifth Generation (5G) era. The low power consumption of the devices allows long battery lifetimes with increasing wireless coverage ranges. This paper presents a comprehensive power consumption model for battery lifetime estimation in narrowband IoT (NB-IoT), which is based on the user equipment (UE) state diagram and considers the extended discontinuous reception (eDRX) and power saving mode (PSM) mechanisms. This model has been used to simulate the effect of varying NB-IoT link parameters, covering a range of values defined in the specification, corresponding to a wide range of applications. Indeed, this study focuses on mathematical analysis of UE power consumption, mainly for NB-IoT communication applications. Repetitions, as defined in the standard, have also been considered in the analysis. Extensive simulations have been carried out to show the power of the proposed model, which provides accurate results for a wide variety of network parameters and let the network designer to select the most appropriated setup. They also show that the value of link parameters must be carefully selected to achieve a battery lifetime of more than a decade with a standard battery of 5 Wh capacity. 

Antonio Torralba

Papers

Learning to Compose Visual Relations.

Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

Pose estimation using radio frequency signals

A latent variable ranking model for content-based retrieval

Energy consumption analytical modeling of NB-IoT devices for diverse IoT applications