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

Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias. Existing work focuses on a handful of curated generative processes which require expert knowledge to design, making it hard to scale up. To overcome this, we propose training with a large dataset of twenty-one thousand programs, each one generating a diverse set of synthetic images. These programs are short code snippets, which are easy to modify and fast to execute using OpenGL. The proposed dataset can be used for both supervised and unsupervised representation learning, and reduces the gap between pre-training with real and procedurally generated images by 38%.

Procedural Image Programs for Representation Learning

Densely and regularly sampled ground-level imagery collected from semi-automated vehicle collection platforms (e.g. Street ViewTM or EarthMineTM) is rapidly becoming available on a global scale. Ground level views of neighborhoods around the world can provide unique regional indicators (e.g. demographics, zoning, socioeconomic health) at a finer resolution than current census data. To this end, this paper introduces the first unsupervised method for automated hierarchical modeling of high-level latent regions using densely sampled, geotagged ground imagery at a global scale. Our unsupervised, nonparametric approach models a multi-scale regularly sampled grid of panoramic ground-level images (where available), producing a multi-scale, multivariate estimate of the latent types of locations (e.g. commercial street, wooded area, park, country road, suburban street, etc.). Region types are model distributions of location types characteristic of particular neighborhoods, towns, or cities. These latent region types are used to cluster all locations into distinct geographic entities with regional signatures that can be used for comparison. We show the effectiveness of this method for discovering regional distributions at vastly different scales, including the Boston area, the United States, and the World.

Unsupervised Non-parametric Geospatial Modeling from Ground Imagery

This paper presents a new family of velocity-tuned filters much simpler than classical Gabor filters used in some motion estimation algorithms. The filters are implemented with analogue networks with asymetrical lateral connexions which allows a complete control of the filter parameters. We present a simple scheme for motion estimation based on analogue networks more efficient for VLSI realisation than methods based on Gabor filters.

http://documents.irevues.inist.fr/bitstream/handle/2042/12693/160_198.pdf?sequence=1

Circuits neuromorphiques pour l'estimation du mouvement

Computer vision has a split personality. Within the same field, and largely guided by the same set of fundamental algorithms, it combines two problems that are utterly disparate in their aims and philosophy—here we will call them “Vision as Measurement” and “Vision as Understanding”. Measurement problems deal with obtaining objective, quantifiable information about the physical world (e.g. scene depth in meters, visual angle in radians, light-source brightness in candelas-per-meter-squared, etc.). Measurement problems are akin to physics—they are well-posed and the validity of a solution can always be testedwith an experiment. Employing careful physical or geometric modeling and rigorous mathematics, this area has been quite successful in solving a number of important problems, such as stereo and structurefrom-motion. Vision as Understanding, on the other hand, has much more to do with psychology and philosophy than physics and mathematics. The goals are defined not in terms of objective quantities, but as subjective, observer-centric tasks. Implicit in tasks such as “find a table in the image” are much deeper issues involving the notion of what is meant by “table”, which could vary across cultures, contexts, and even individual observers. Because of this, approaches based on concise models and elegant mathematics, that proved so successful at

http://dspace.mit.edu/openaccess-disseminate/1721.1/103786

Guest Editorial: Big Data

We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs have a natural way to support a dynamically-growing number of tasks and classes and less interference with old tasks. We show that EBMs are adaptable to a more general continual learning setting where the data distribution changes without the notion of explicitly delineated tasks. We also find that EBMs outperform the baseline methods by a large margin on several continual learning benchmarks. These observations point towards EBMs as a class of models naturally inclined towards the continual learning regime.

/pdf/energy-based-models-for-continual-learning-4m1ufjqelk.pdf

Antonio Torralba

Papers

Procedural Image Programs for Representation Learning

Unsupervised Non-parametric Geospatial Modeling from Ground Imagery

Circuits neuromorphiques pour l'estimation du mouvement

Guest Editorial: Big Data

Energy-Based Models for Continual Learning