arXiv subjects

René Vidal

Publications and source records attributed to René Vidal.

85 records · Page 5Linked to original sources

arXiv2018

Monocular Object Orientation Estimation using Riemannian Regression and Classification Networks

We consider the task of estimating the 3D orientation of an object of known category given an image of the object and a bounding box around it. Recently, CNN-based regression and classification methods have shown significant performance improvements for this task. This paper proposes a new CNN-based approach to monocular orientation estimation that advances the state of the art in four different directions. First, we take into account the Riemannian structure of the orientation space when designing regression losses and nonlinear activation functions. Second, we propose a mixed Riemannian regression and classification framework that better handles the challenging case of nearly symmetric objects. Third, we propose a data augmentation strategy that is specifically designed to capture changes in 3D orientation. Fourth, our approach leads to state-of-the-art results on the PASCAL3D+ dataset.

cs.CV↗

arXiv2018

Joint Spatial-Angular Sparse Coding for dMRI with Separable Dictionaries

Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, $\textit{in vivo}$, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation than the popularly used diffusion tensor imaging, but the high number of samples needed to estimate diffusivity requires longer patient scan times. To accelerate dMRI, compressed sensing (CS) has been utilized by exploiting a sparse dictionary representation of the data, discovered through sparse coding. The sparser the representation, the fewer samples are needed to reconstruct a high resolution signal with limited information loss, and so an important area of research has focused on finding the sparsest possible representation of dMRI. Current reconstruction methods however, rely on an angular representation $\textit{per voxel}$ with added spatial regularization, and so, for non-zero signals, one is required to have at least one non-zero coefficient per voxel. This means that the global level of sparsity must be greater than the number of voxels. In contrast, we propose a joint spatial-angular representation of dMRI that will allow us to achieve levels of global sparsity that are below the number of voxels. A major challenge, however, is the computational complexity of solving a global sparse coding problem over large-scale dMRI. In this work, we present novel adaptations of popular sparse coding algorithms that become better suited for solving large-scale problems by exploiting spatial-angular separability. Our experiments show that our method achieves significantly sparser representations of HARDI than is possible by the state of the art.

stat.ML↗

arXiv2018

End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding

Fine-grained action segmentation and recognition is an important yet challenging task. Given a long, untrimmed sequence of kinematic data, the task is to classify the action at each time frame and segment the time series into the correct sequence of actions. In this paper, we propose a novel framework that combines a temporal Conditional Random Field (CRF) model with a powerful frame-level representation based on discriminative sparse coding. We introduce an end-to-end algorithm for jointly learning the weights of the CRF model, which include action classification and action transition costs, as well as an overcomplete dictionary of mid-level action primitives. This results in a CRF model that is driven by sparse coding features obtained using a discriminative dictionary that is shared among different actions and adapted to the task of structured output learning. We evaluate our method on three surgical tasks using kinematic data from the JIGSAWS dataset, as well as on a food preparation task using accelerometer data from the 50 Salads dataset. Our results show that the proposed method performs on par or better than state-of-the-art methods.

cs.CV↗

arXiv2017

An Analysis of Dropout for Matrix Factorization

Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem classes, such as linear or logistic regression, several theoretical studies have demonstrated the equivalence between dropout and a fully deterministic optimization problem with data-dependent Tikhonov regularization. This work presents a theoretical analysis of dropout for matrix factorization, where Bernoulli random variables are used to drop a factor, thereby attempting to control the size of the factorization. While recent work has demonstrated the empirical effectiveness of dropout for matrix factorization, a theoretical understanding of the regularization properties of dropout in this context remains elusive. This work demonstrates the equivalence between dropout and a fully deterministic model for matrix factorization in which the factors are regularized by the sum of the product of the norms of the columns. While the resulting regularizer is closely related to a variational form of the nuclear norm, suggesting that dropout may limit the size of the factorization, we show that it is possible to trivially lower the objective value by doubling the size of the factorization. We show that this problem is caused by the use of a fixed dropout rate, which motivates the use of a rate that increases with the size of the factorization. Synthetic experiments validate our theoretical findings.

cs.LG↗

arXiv2017

(k,q)-Compressed Sensing for dMRI with Joint Spatial-Angular Sparsity Prior

Advanced diffusion magnetic resonance imaging (dMRI) techniques, like diffusion spectrum imaging (DSI) and high angular resolution diffusion imaging (HARDI), remain underutilized compared to diffusion tensor imaging because the scan times needed to produce accurate estimations of fiber orientation are significantly longer. To accelerate DSI and HARDI, recent methods from compressed sensing (CS) exploit a sparse underlying representation of the data in the spatial and angular domains to undersample in the respective k- and q-spaces. State-of-the-art frameworks, however, impose sparsity in the spatial and angular domains separately and involve the sum of the corresponding sparse regularizers. In contrast, we propose a unified (k,q)-CS formulation which imposes sparsity jointly in the spatial-angular domain to further increase sparsity of dMRI signals and reduce the required subsampling rate. To efficiently solve this large-scale global reconstruction problem, we introduce a novel adaptation of the FISTA algorithm that exploits dictionary separability. We show on phantom and real HARDI data that our approach achieves significantly more accurate signal reconstructions than the state of the art while sampling only 2-4% of the (k,q)-space, allowing for the potential of new levels of dMRI acceleration.

cs.CV↗

arXiv2017

Provable Self-Representation Based Outlier Detection in a Union of Subspaces

Many computer vision tasks involve processing large amounts of data contaminated by outliers, which need to be detected and rejected. While outlier detection methods based on robust statistics have existed for decades, only recently have methods based on sparse and low-rank representation been developed along with guarantees of correct outlier detection when the inliers lie in one or more low-dimensional subspaces. This paper proposes a new outlier detection method that combines tools from sparse representation with random walks on a graph. By exploiting the property that data points can be expressed as sparse linear combinations of each other, we obtain an asymmetric affinity matrix among data points, which we use to construct a weighted directed graph. By defining a suitable Markov Chain from this graph, we establish a connection between inliers/outliers and essential/inessential states of the Markov chain, which allows us to detect outliers by using random walks. We provide a theoretical analysis that justifies the correctness of our method under geometric and connectivity assumptions. Experimental results on image databases demonstrate its superiority with respect to state-of-the-art sparse and low-rank outlier detection methods.

cs.CV↗

arXiv2017

Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework

Subspace clustering refers to the problem of segmenting data drawn from a union of subspaces. State-of-the-art approaches for solving this problem follow a two-stage approach. In the first step, an affinity matrix is learned from the data using sparse or low-rank minimization techniques. In the second step, the segmentation is found by applying spectral clustering to this affinity. While this approach has led to state-of-the-art results in many applications, it is sub-optimal because it does not exploit the fact that the affinity and the segmentation depend on each other. In this paper, we propose a joint optimization framework --- Structured Sparse Subspace Clustering (S$^3$C) --- for learning both the affinity and the segmentation. The proposed S$^3$C framework is based on expressing each data point as a structured sparse linear combination of all other data points, where the structure is induced by a norm that depends on the unknown segmentation. Moreover, we extend the proposed S$^3$C framework into Constrained Structured Sparse Subspace Clustering (CS$^3$C) in which available partial side-information is incorporated into the stage of learning the affinity. We show that both the structured sparse representation and the segmentation can be found via a combination of an alternating direction method of multipliers with spectral clustering. Experiments on a synthetic data set, the Extended Yale B data set, the Hopkins 155 motion segmentation database, and three cancer data sets demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2016

Realization Theory of Stochastic Jump-Markov Linear Systems

In this paper, we present a complete stochastic realization theory for stochastic jump-linear systems. We present necessary and sufficient conditions for the existence of a realization, along with a characterization of minimality in terms of reachability and observability. We also formulate a realization algorithm and argue that minimality can be checked algorithmically. The main tool for solving the stochastic realization problem for jump-linear systems is the formulation and solution of a stochastic realization problem for a general class of bilinear systems with non-white-noise inputs. The solution to this generalized stochastic bilinear realization problem is based on the theory of formal power series. Stochastic jump-linear systems represent a special case of generalized stochastic bilinear systems.

math.OC↗

arXiv2016

Car Segmentation and Pose Estimation using 3D Object Models

Image segmentation and 3D pose estimation are two key cogs in any algorithm for scene understanding. However, state-of-the-art CRF-based models for image segmentation rely mostly on 2D object models to construct top-down high-order potentials. In this paper, we propose new top-down potentials for image segmentation and pose estimation based on the shape and volume of a 3D object model. We show that these complex top-down potentials can be easily decomposed into standard forms for efficient inference in both the segmentation and pose estimation tasks. Experiments on a car dataset show that knowledge of segmentation helps perform pose estimation better and vice versa.

cs.CV↗

arXiv2012

Riemannian Consensus for Manifolds with Bounded Curvature

Consensus algorithms are popular distributed algorithms for computing aggregate quantities, such as averages, in ad-hoc wireless networks. However, existing algorithms mostly address the case where the measurements lie in a Euclidean space. In this work we propose Riemannian consensus, a natural extension of the existing averaging consensus algorithm to the case of Riemannian manifolds. Unlike previous generalizations, our algorithm is intrinsic and, in principle, can be applied to any complete Riemannian manifold. We characterize our algorithm by giving sufficient convergence conditions on Riemannian manifolds with bounded curvature and we analyze the differences that rise with respect to the classical Euclidean case. We test the proposed algorithms on synthetic data sampled from manifolds such as the space of rotations, the sphere and the Grassmann manifold.

math.DS↗

arXiv2011

On The Convergence of Gradient Descent for Finding the Riemannian Center of Mass

We study the problem of finding the global Riemannian center of mass of a set of data points on a Riemannian manifold. Specifically, we investigate the convergence of constant step-size gradient descent algorithms for solving this problem. The challenge is that often the underlying cost function is neither globally differentiable nor convex, and despite this one would like to have guaranteed convergence to the global minimizer. After some necessary preparations we state a conjecture which we argue is the best (in a sense described) convergence condition one can hope for. The conjecture specifies conditions on the spread of the data points, step-size range, and the location of the initial condition (i.e., the region of convergence) of the algorithm. These conditions depend on the topology and the curvature of the manifold and can be conveniently described in terms of the injectivity radius and the sectional curvatures of the manifold. For manifolds of constant nonnegative curvature (e.g., the sphere and the rotation group in $\mathbb{R}^{3}$) we show that the conjecture holds true (we do this by proving and using a comparison theorem which seems to be of a different nature from the standard comparison theorems in Riemannian geometry). For manifolds of arbitrary curvature we prove convergence results which are weaker than the conjectured one (but still superior over the available results). We also briefly study the effect of the configuration of the data points on the speed of convergence.

math.DG↗

arXiv2011

Hypothesize and Bound: A Computational Focus of Attention Mechanism for Simultaneous 3D Shape Reconstruction, Pose Estimation and Classification from a Single 2D Image

This article presents a mathematical framework to simultaneously tackle the problems of 3D reconstruction, pose estimation and object classification, from a single 2D image. In sharp contrast with state of the art methods that rely primarily on 2D information and solve each of these three problems separately or iteratively, we propose a mathematical framework that incorporates prior "knowledge" about the 3D shapes of different object classes and solves these problems jointly and simultaneously, using a hypothesize-and-bound (H&B) algorithm. In the proposed H&B algorithm one hypothesis is defined for each possible pair [object class, object pose], and the algorithm selects the hypothesis H that maximizes a function L(H) encoding how well each hypothesis "explains" the input image. To find this maximum efficiently, the function L(H) is not evaluated exactly for each hypothesis H, but rather upper and lower bounds for it are computed at a much lower cost. In order to obtain bounds for L(H) that are tight yet inexpensive to compute, we extend the theory of shapes described in [14] to handle projections of shapes. This extension allows us to define a probabilistic relationship between the prior knowledge given in 3D and the 2D input image. This relationship is derived from first principles and is proven to be the only relationship having the properties that we intuitively expect from a "projection." In addition to the efficiency and optimality characteristics of H&B algorithms, the proposed framework has the desirable property of integrating information in the 2D image with information in the 3D prior to estimate the optimal reconstruction. While this article focuses primarily on the problem mentioned above, we believe that the theory presented herein has multiple other potential applications.

cs.CV↗

arXiv2011

Hypothesize and Bound: A Computational Focus of Attention Mechanism for Simultaneous N-D Segmentation, Pose Estimation and Classification Using Shape Priors

Given the ever increasing bandwidth of the visual information available to many intelligent systems, it is becoming essential to endow them with a sense of what is worthwhile their attention and what can be safely disregarded. This article presents a general mathematical framework to efficiently allocate the available computational resources to process the parts of the input that are relevant to solve a given perceptual problem. By this we mean to find the hypothesis H (i.e., the state of the world) that maximizes a function L(H), representing how well each hypothesis "explains" the input. Given the large bandwidth of the sensory input, fully evaluating L(H) for each hypothesis H is computationally infeasible (e.g., because it would imply checking a large number of pixels). To address this problem we propose a mathematical framework with two key ingredients. The first one is a Bounding Mechanism (BM) to compute lower and upper bounds of L(H), for a given computational budget. These bounds are much cheaper to compute than L(H) itself, can be refined at any time by increasing the budget allocated to a hypothesis, and are frequently enough to discard a hypothesis. To compute these bounds, we develop a novel theory of shapes and shape priors. The second ingredient is a Focus of Attention Mechanism (FoAM) to select which hypothesis' bounds should be refined next, with the goal of discarding non-optimal hypotheses with the least amount of computation. The proposed framework: 1) is very efficient since most hypotheses are discarded with minimal computation; 2) is parallelizable; 3) is guaranteed to find the globally optimal hypothesis; and 4) its running time depends on the problem at hand, not on the bandwidth of the input. We instantiate the proposed framework for the problem of simultaneously estimating the class, pose, and a noiseless version of a 2D shape in a 2D image.

cs.CV↗