Andrew Zisserman

Bio: Andrew Zisserman is an academic researcher from University of Oxford. The author has contributed to research in topics: Real image & Convolutional neural network. The author has an hindex of 167, co-authored 808 publications receiving 261717 citations. Previous affiliations of Andrew Zisserman include University of Edinburgh & Microsoft.

Learning class-specific edges for object detection and segmentation

Abstract: Recent research into recognizing object classes (such as humans, cows and hands) has made use of edge features to hypothesize and localize class instances. However, for the most part, these edge-based methods operate solely on the geometric shape of edges, treating them equally and ignoring the fact that for certain object classes, the appearance of the object on the “inside” of the edge may provide valuable recognition cues. We show how, for such object classes, small regions around edges can be used to classify the edge into object or non-object. This classifier may then be used to prune edges which are not relevant to the object class, and thereby improve the performance of subsequent processing. We demonstrate learning class specific edges for a number of object classes — oranges, bananas and bottles — under challenging scale and illumination variation. Because class-specific edge classification provides a low-level analysis of the image it may be integrated into any edge-based recognition strategy without significant change in the high-level algorithms. We illustrate its application to two algorithms: (i) chamfer matching for object detection, and (ii) modulating contrast terms in MRF based object-specific segmentation. We show that performance of both algorithms (matching and segmentation) is considerably improved by the class-specific edge labelling.

Learning epipolar geometry from image sequences

Abstract: We wish to determine the epipolar geometry of a stereo camera pair from image measurements alone. This paper describes a solution to this problem, which does not require a parametric model of the camera system, and consequently applies equally well to a wide class of stereo configurations. Examples in the paper range from a standard pinhole stereo configuration to more exotic systems combining curved mirrors and wide-angle lenses. The method described here allows epipolar curves to be learnt from multiple image pairs acquired by stereo cameras with fixed configuration. By aggregating information over the multiple image pairs, a dense map of the epipolar curves can be determined on the images. The algorithm requires a large number of images, but has the distinct benefit that the correspondence problem does not have to be explicitly solved. We show that for standard stereo configurations the results are comparable to those obtained from a state of the art parametric model method, despite the significantly weaker constraints on the non-parametric model. The new algorithm is simple to implement, so it may easily be employed on a new and possibly complex camera system.

Optimizing and Learning for Super-resolution.

Abstract: In multiple-image super-resolution, a high resolution image is estimated from a number of lower-resolution images. This involves computing the parameters of a generative imaging model (such as geometric and photometric registration, and blur) and obtaining a MAP estimate by minimizing a cost function including an appropriate prior. We consider the quite general geometric registration situation modelled by a plane projective transformation, and make two novel contributions: (i) in previous approaches the MAP estimate has been obtained by fir st computing and fixing the registration, and then computing the super-re solution image with this registration. We demonstrate that superior estim ates are obtained by optimizing over both the registration and image; (ii) the parameters of the edge preserving prior are learnt automatically from the data, rather than being set by trial and error. We show examples on a number of real sequences including multiple stills, digital video, and DVDs of movies.

Deep Residual Learning for Image Recognition

Abstract: 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.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Abstract: 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

Abstract: 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.

ImageNet: A large-scale hierarchical image database

Abstract: 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.

U-Net: Convolutional Networks for Biomedical Image Segmentation

Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .