Andrew Zisserman

The Pascal Visual Object Classes (VOC) Challenge

The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection.This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.

Object class recognition by unsupervised scale-invariant learning

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

Return of the Devil in the Details: Delving Deep into Convolutional Nets.

The latest generation of Convolutional Neural Networks (CNN) have achieved impressive results in challenging benchmarks on image recognition and object detection, significantly raising the interest of the community in these methods. Nevertheless, it is still unclear how different CNN methods compare with each other and with previous state-of-the-art shallow representations such as the Bag-of-Visual-Words and the Improved Fisher Vector. This paper conducts a rigorous evaluation of these new techniques, exploring different deep architectures and comparing them on a common ground, identifying and disclosing important implementation details. We identify several useful properties of CNN-based representations, including the fact that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance. We also identify aspects of deep and shallow methods that can be successfully shared. In particular, we show that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost. Source code and models to reproduce the experiments in the paper is made publicly available.

MLESAC: A New Robust Estimator with Application to Estimating Image Geometry

Abstract A new method is presented for robustly estimating multiple view relations from point correspondences. The method comprises two parts. The first is a new robust estimator MLESAC which is a generalization of the RANSAC estimator. It adopts the same sampling strategy as RANSAC to generate putative solutions, but chooses the solution that maximizes the likelihood rather than just the number of inliers. The second part of the algorithm is a general purpose method for automatically parameterizing these relations, using the output of MLESAC. A difficulty with multiview image relations is that there are often nonlinear constraints between the parameters, making optimization a difficult task. The parameterization method overcomes the difficulty of nonlinear constraints and conducts a constrained optimization. The method is general and its use is illustrated for the estimation of fundamental matrices, image–image homographies, and quadratic transformations. Results are given for both synthetic and real images. It is demonstrated that the method gives results equal or superior to those of previous approaches.

Representing shape with a spatial pyramid kernel

The objective of this paper is classifying images by the object categories they contain, for example motorbikes or dolphins. There are three areas of novelty. First, we introduce a descriptor that represents local image shape and its spatial layout, together with a spatial pyramid kernel. These are designed so that the shape correspondence between two images can be measured by the distance between their descriptors using the kernel. Second, we generalize the spatial pyramid kernel, and learn its level weighting parameters (on a validation set). This significantly improves classification performance. Third, we show that shape and appearance kernels may be combined (again by learning parameters on a validation set). Results are reported for classification on Caltech-101 and retrieval on the TRECVID 2006 data sets. For Caltech-101 it is shown that the class specific optimization that we introduce exceeds the state of the art performance by more than 10%.

Lost in quantization: Improving particular object retrieval in large scale image databases

The state of the art in visual object retrieval from large databases is achieved by systems that are inspired by text retrieval. A key component of these approaches is that local regions of images are characterized using high-dimensional descriptors which are then mapped to ldquovisual wordsrdquo selected from a discrete vocabulary.This paper explores techniques to map each visual region to a weighted set of words, allowing the inclusion of features which were lost in the quantization stage of previous systems. The set of visual words is obtained by selecting words based on proximity in descriptor space. We describe how this representation may be incorporated into a standard tf-idf architecture, and how spatial verification is modified in the case of this soft-assignment. We evaluate our method on the standard Oxford Buildings dataset, and introduce a new dataset for evaluation. Our results exceed the current state of the art retrieval performance on these datasets, particularly on queries with poor initial recall where techniques like query expansion suffer. Overall we show that soft-assignment is always beneficial for retrieval with large vocabularies, at a cost of increased storage requirements for the index.

A Statistical Approach to Texture Classification from Single Images

We investigate texture classification from single images obtained under unknown viewpoint and illumination. A statistical approach is developed where textures are modelled by the joint probability distribution of filter responses. This distribution is represented by the frequency histogram of filter response cluster centres (textons). Recognition proceeds from single, uncalibrated images and the novelty here is that rotationally invariant filters are used and the filter response space is low dimensional.Classification performance is compared with the filter banks and methods of Leung and Malik [IJCV, 2001], Schmid [CVPR, 2001] and Cula and Dana [IJCV, 2004] and it is demonstrated that superior performance is achieved here. Classification results are presented for all 61 materials in the Columbia-Utrecht texture database.We also discuss the effects of various parameters on our classification algorithm—such as the choice of filter bank and rotational invariance, the size of the texton dictionary as well as the number of training images used. Finally, we present a method of reliably measuring relative orientation co-occurrence statistics in a rotationally invariant manner, and discuss whether incorporating such information can enhance the classifier’s performance.

Non-local sparse models for image restoration

We propose in this paper to unify two different approaches to image restoration: On the one hand, learning a basis set (dictionary) adapted to sparse signal descriptions has proven to be very effective in image reconstruction and classification tasks. On the other hand, explicitly exploiting the self-similarities of natural images has led to the successful non-local means approach to image restoration. We propose simultaneous sparse coding as a framework for combining these two approaches in a natural manner. This is achieved by jointly decomposing groups of similar signals on subsets of the learned dictionary. Experimental results in image denoising and demosaicking tasks with synthetic and real noise show that the proposed method outperforms the state of the art, making it possible to effectively restore raw images from digital cameras at a reasonable speed and memory cost.

Image Classification using Random Forests and Ferns

We explore the problem of classifying images by the object categories they contain in the case of a large number of object categories. To this end we combine three ingredients: (i) shape and appearance representations that support spatial pyramid matching over a region of interest. This generalizes the representation of Lazebnik et al., (2006) from an image to a region of interest (ROI), and from appearance (visual words) alone to appearance and local shape (edge distributions); (ii) automatic selection of the regions of interest in training. This provides a method of inhibiting background clutter and adding invariance to the object instance s position; and (iii) the use of random forests (and random ferns) as a multi-way classifier. The advantage of such classifiers (over multi-way SVM for example) is the ease of training and testing. Results are reported for classification of the Caltech-101 and Caltech-256 data sets. We compare the performance of the random forest/ferns classifier with a benchmark multi-way SVM classifier. It is shown that selecting the ROI adds about 5% to the performance and, together with the other improvements, the result is about a 10% improvement over the state of the art for Caltech-256.

Deep Face Recognition.

The goal of this paper is face recognition – from either a single photograph or from a set of faces tracked in a video. Recent progress in this area has been due to two factors: (i) end to end learning for the task using a convolutional neural network (CNN), and (ii) the availability of very large scale training datasets. We make two contributions: first, we show how a very large scale dataset (2.6M images, over 2.6K people) can be assembled by a combination of automation and human in the loop, and discuss the trade off between data purity and time; second, we traverse through the complexities of deep network training and face recognition to present methods and procedures to achieve comparable state of the art results on the standard LFW and YTF face benchmarks.