Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

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

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

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

Systems, methods, and non-transitory computer-readable media can receive a first image including a representation of a first user. A second image including a representation of a second user can be received. A first set of poselets associated with the first user can be detected in the first image. A second set of poselets associated with the second user can be detected in the second image. The first image including the first set of poselets can be inputted into a first instance of a neural network to generate a first multi-dimensional vector. The second image including the second set of poselets can be inputted into a second instance of the neural network to generate a second multi-dimensional vector. A first distance metric between the first multi-dimensional vector and the second multi-dimensional vector can be determined.

Systems and methods for identifying users in media content based on poselets and neural networks

Kepler's immense photometric precision to date was maintained through satellite stability and precise pointing. In this white paper, we argue that image modeling--fitting the Kepler-downlinked raw pixel data--can vastly improve the precision of Kepler in pointing-degraded two-wheel mode. We argue that a non-trivial modeling effort may permit continuance of photometry at 10-ppm-level precision. We demonstrate some baby steps towards precise models in both data-driven (flexible) and physics-driven (interpretably parameterized) modes. We demonstrate that the expected drift or jitter in positions in the two-weel era will help with constraining calibration parameters. In particular, we show that we can infer the device flat-field at higher than pixel resolution; that is, we can infer pixel-to-pixel variations in intra-pixel sensitivity. These results are relevant to almost any scientific goal for the repurposed mission; image modeling ought to be a part of any two-wheel repurpose for the satellite. We make other recommendations for Kepler operations, but fundamentally advocate that the project stick with its core mission of finding and characterizing Earth analogs. [abridged]

Maximizing Kepler science return per telemetered pixel: Detailed models of the focal plane in the two-wheel era

/pdf/understanding-the-asymptotic-performance-of-model-based-rl-4pzn9vpwbn.pdf

Understanding the Asymptotic Performance of Model-Based RL Methods

High dynamic-range imagers aim to block out or null light from a very bright primary star to make it possible to detect and measure far fainter companions; in real systems a small fraction of the primary light is scattered, diffracted, and unocculted. We introduce S4, a flexible data-driven model for the unocculted (and highly speckled) light in the P1640 spectroscopic coronograph. The model uses Principal Components Analysis (PCA) to capture the spatial structure and wavelength dependence of the speckles but not the signal produced by any companion. Consequently, the residual typically includes the companion signal. The companion can thus be found by filtering this error signal with a fixed companion model. The approach is sensitive to companions that are of order a percent of the brightness of the speckles, or up to $10^{-7}$ times the brightness of the primary star. This outperforms existing methods by a factor of 2-3 and is close to the shot-noise physical limit.

S4: A Spatial-Spectral model for Speckle Suppression

With the widespread availability of cellphones and cameras that have GPS capabilities, it is common for images being uploaded to the Internet today to have GPS coordinates associated with them. In addition to research that tries to predict GPS coordinates from visual features, this also opens up the door to problems that are conditioned on the availability of GPS coordinates. In this work, we tackle the problem of performing image classification with location context, in which we are given the GPS coordinates for images in both the train and test phases. We explore different ways of encoding and extracting features from the GPS coordinates, and show how to naturally incorporate these features into a Convolutional Neural Network (CNN), the current state-of-the-art for most image classification and recognition problems. We also show how it is possible to simultaneously learn the optimal pooling radii for a subset of our features within the CNN framework. To evaluate our model and to help promote research in this area, we identify a set of location-sensitive concepts and annotate a subset of the Yahoo Flickr Creative Commons 100M dataset that has GPS coordinates with these concepts, which we make publicly available. By leveraging location context, we are able to achieve almost a 7% gain in mean average precision.

Rob Fergus

Papers

Systems and methods for identifying users in media content based on poselets and neural networks

Maximizing Kepler science return per telemetered pixel: Detailed models of the focal plane in the two-wheel era

Understanding the Asymptotic Performance of Model-Based RL Methods

S4: A Spatial-Spectral model for Speckle Suppression

Improving Image Classification with Location Context