Andrea Vedaldi

Vlfeat: an open and portable library of computer vision algorithms

VLFeat is an open and portable library of computer vision algorithms. It aims at facilitating fast prototyping and reproducible research for computer vision scientists and students. It includes rigorous implementations of common building blocks such as feature detectors, feature extractors, (hierarchical) k-means clustering, randomized kd-tree matching, and super-pixelization. The source code and interfaces are fully documented. The library integrates directly with MATLAB, a popular language for computer vision research.

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.

MatConvNet: Convolutional Neural Networks for MATLAB

MatConvNet is an open source implementation of Convolutional Neural Networks (CNNs) with a deep integration in the MATLAB environment. The toolbox is designed with an emphasis on simplicity and flexibility. It exposes the building blocks of CNNs as easy-to-use MATLAB functions, providing routines for computing convolutions with filter banks, feature pooling, normalisation, and much more. MatConvNet can be easily extended, often using only MATLAB code, allowing fast prototyping of new CNN architectures. At the same time, it supports efficient computation on CPU and GPU, allowing to train complex models on large datasets such as ImageNet ILSVRC containing millions of training examples

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.

The devil is in the details: an evaluation of recent feature encoding methods

A large number of novel encodings for bag of visual words models have been proposed in the past two years to improve on the standard histogram of quantized local features. Examples include locality-constrained linear encoding [23], improved Fisher encoding [17], super vector encoding [27], and kernel codebook encoding [20]. While several authors have reported very good results on the challenging PASCAL VOC classification data by means of these new techniques, differences in the feature computation and learning algorithms, missing details in the description of the methods, and different tuning of the various components, make it impossible to compare directly these methods and hard to reproduce the results reported. This paper addresses these shortcomings by carrying out a rigorous evaluation of these new techniques by: (1) fixing the other elements of the pipeline (features, learning, tuning); (2) disclosing all the implementation details, and (3) identifying both those aspects of each method which are particularly important to achieve good performance, and those aspects which are less critical. This allows a consistent comparative analysis of these encoding methods. Several conclusions drawn from our analysis cannot be inferred from the original publications.

Multiple kernels for object detection

Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image sub-windows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential χ2 kernels, each of which captures a different feature channel. Our features include the distribution of edges, dense and sparse visual words, and feature descriptors at different levels of spatial organization.

Efficient Additive Kernels via Explicit Feature Maps

Large scale nonlinear support vector machines (SVMs) can be approximated by linear ones using a suitable feature map. The linear SVMs are in general much faster to learn and evaluate (test) than the original nonlinear SVMs. This work introduces explicit feature maps for the additive class of kernels, such as the intersection, Hellingers, and χ2 kernels, commonly used in computer vision, and enables their use in large scale problems. In particular, we: 1) provide explicit feature maps for all additive homogeneous kernels along with closed form expression for all common kernels; 2) derive corresponding approximate finite-dimensional feature maps based on a spectral analysis; and 3) quantify the error of the approximation, showing that the error is independent of the data dimension and decays exponentially fast with the approximation order for selected kernels such as χ2. We demonstrate that the approximations have indistinguishable performance from the full kernels yet greatly reduce the train/test times of SVMs. We also compare with two other approximation methods: Nystroms approximation of Perronnin et al., which is data dependent, and the explicit map of Maji and Berg for the intersection kernel, which, as in the case of our approximations, is data independent. The approximations are evaluated on a number of standard data sets, including Caltech-101, Daimler-Chrysler pedestrians, and INRIA pedestrians.

Class segmentation and object localization with superpixel neighborhoods

We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by aggregating histograms in the neighborhood of each superpixel and then refine our results further by using the classifier in a conditional random field operating on the superpixel graph. Our proposed method exceeds the previously published state-of-the-art on two challenging datasets: Graz-02 and the PASCAL VOC 2007 Segmentation Challenge.

Quick Shift and Kernel Methods for Mode Seeking

We show that the complexity of the recently introduced medoid-shift algorithm in clustering N points is O(N 2), with a small constant, if the underlying distance is Euclidean. This makes medoid shift considerably faster than mean shift, contrarily to what previously believed. We then exploit kernel methods to extend both mean shift and the improved medoid shift to a large family of distances, with complexity bounded by the effective rank of the resulting kernel matrix, and with explicit regularization constraints. Finally, we show that, under certain conditions, medoid shift fails to cluster data points belonging to the same mode, resulting in over-fragmentation. We propose remedies for this problem, by introducing a novel, simple and extremely efficient clustering algorithm, called quick shift, that explicitly trades off under- and over-fragmentation. Like medoid shift, quick shift operates in non-Euclidean spaces in a straightforward manner. We also show that the accelerated medoid shift can be used to initialize mean shift for increased efficiency. We illustrate our algorithms to clustering data on manifolds, image segmentation, and the automatic discovery of visual categories.

Understanding deep image representations by inverting them

Image representations, from SIFT and Bag of Visual Words to Convolutional Neural Networks (CNNs), are a crucial component of almost any image understanding system. Nevertheless, our understanding of them remains limited. In this paper we conduct a direct analysis of the visual information contained in representations by asking the following question: given an encoding of an image, to which extent is it possible to reconstruct the image itself? To answer this question we contribute a general framework to invert representations. We show that this method can invert representations such as HOG more accurately than recent alternatives while being applicable to CNNs too. We then use this technique to study the inverse of recent state-of-the-art CNN image representations for the first time. Among our findings, we show that several layers in CNNs retain photographically accurate information about the image, with different degrees of geometric and photometric invariance.