arXiv subjects

Trac D. Tran

Publications and source records attributed to Trac D. Tran.

35 records · Page 2Linked to original sources

arXiv2017

Supervised Deep Sparse Coding Networks

In this paper, we describe the deep sparse coding network (SCN), a novel deep network that encodes intermediate representations with nonnegative sparse coding. The SCN is built upon a number of cascading bottleneck modules, where each module consists of two sparse coding layers with relatively wide and slim dictionaries that are specialized to produce high dimensional discriminative features and low dimensional representations for clustering, respectively. During training, both the dictionaries and regularization parameters are optimized with an end-to-end supervised learning algorithm based on multilevel optimization. Effectiveness of an SCN with seven bottleneck modules is verified on several popular benchmark datasets. Remarkably, with few parameters to learn, our SCN achieves 5.81% and 19.93% classification error rate on CIFAR-10 and CIFAR-100, respectively.

cs.CV↗

arXiv2017

Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization

Automatic localization and labeling of vertebra in 3D medical images plays an important role in many clinical tasks, including pathological diagnosis, surgical planning and postoperative assessment. However, the unusual conditions of pathological cases, such as the abnormal spine curvature, bright visual imaging artifacts caused by metal implants, and the limited field of view, increase the difficulties of accurate localization. In this paper, we propose an automatic and fast algorithm to localize and label the vertebra centroids in 3D CT volumes. First, we deploy a deep image-to-image network (DI2IN) to initialize vertebra locations, employing the convolutional encoder-decoder architecture together with multi-level feature concatenation and deep supervision. Next, the centroid probability maps from DI2IN are iteratively evolved with the message passing schemes based on the mutual relation of vertebra centroids. Finally, the localization results are refined with sparsity regularization. The proposed method is evaluated on a public dataset of 302 spine CT volumes with various pathologies. Our method outperforms other state-of-the-art methods in terms of localization accuracy. The run time is around 3 seconds on average per case. To further boost the performance, we retrain the DI2IN on additional 1000+ 3D CT volumes from different patients. To the best of our knowledge, this is the first time more than 1000 3D CT volumes with expert annotation are adopted in experiments for the anatomic landmark detection tasks. Our experimental results show that training with such a large dataset significantly improves the performance and the overall identification rate, for the first time by our knowledge, reaches 90 %.

cs.CV↗

arXiv2017

Sparse Signal Recovery using Generalized Approximate Message Passing with Built-in Parameter Estimation

The generalized approximate message passing (GAMP) algorithm under the Bayesian setting shows advantage in recovering under-sampled sparse signals from corrupted observations. Compared to conventional convex optimization methods, it has a much lower complexity and is computationally tractable. In the GAMP framework, the sparse signal and the observation are viewed to be generated according to some pre-specified probability distributions in the input and output channels. However, the parameters of the distributions are usually unknown in practice. In this paper, we propose an extended GAMP algorithm with built-in parameter estimation (PE-GAMP) and present its empirical convergence analysis. PE-GAMP treats the parameters as unknown random variables with simple priors and jointly estimates them with the sparse signals. Compared with Expectation Maximization (EM) based parameter estimation methods, the proposed PE-GAMP could draw information from the prior distributions of the parameters to perform parameter estimation. It is also more robust and much simpler, which enables us to consider more complex signal distributions apart from the usual Bernoulli-Gaussian (BGm) mixture distribution. Specifically, the formulations of Bernoulli-Exponential mixture (BEm) distribution and Laplace distribution are given in this paper. Simulated noiseless sparse signal recovery experiments demonstrate that the performance of the proposed PE-GAMP matches the oracle GAMP algorithm. When noise is present, both the simulated experiments and the real image recovery experiments show that PE-GAMP is still able to maintain its robustness and outperform EM based parameter estimation method when the sampling ratio is small. Additionally, using the BEm formulation of the PE-GAMP, we can successfully perform non-negative sparse coding of local image patches and provide useful features for the image classification task.

cs.IT↗

arXiv2017

Linear Disentangled Representation Learning for Facial Actions

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters normally is not demanding in terms of training data. In this paper, we propose an elegant linear model to untangle confounding factors in challenging realistic multichannel signals such as 2D face videos. The simple yet powerful model does not rely on huge training data and is natural for recognizing facial actions without explicitly disentangling the identity. Base on well-understood intuitive linear models such as Sparse Representation based Classification (SRC), previous attempts require a prepossessing of explicit decoupling which is practically inexact. Instead, we exploit the low-rank property across frames to subtract the underlying neutral faces which are modeled jointly with sparse representation on the action components with group sparsity enforced. On the extended Cohn-Kanade dataset (CK+), our one-shot automatic method on raw face videos performs as competitive as SRC applied on manually prepared action components and performs even better than SRC in terms of true positive rate. We apply the model to the even more challenging task of facial action unit recognition, verified on the MPI Face Video Database (MPI-VDB) achieving a decent performance. All the programs and data have been made publicly available.

cs.CV↗

arXiv2016

Pose-Selective Max Pooling for Measuring Similarity

In this paper, we deal with two challenges for measuring the similarity of the subject identities in practical video-based face recognition - the variation of the head pose in uncontrolled environments and the computational expense of processing videos. Since the frame-wise feature mean is unable to characterize the pose diversity among frames, we define and preserve the overall pose diversity and closeness in a video. Then, identity will be the only source of variation across videos since the pose varies even within a single video. Instead of simply using all the frames, we select those faces whose pose point is closest to the centroid of the K-means cluster containing that pose point. Then, we represent a video as a bag of frame-wise deep face features while the number of features has been reduced from hundreds to K. Since the video representation can well represent the identity, now we measure the subject similarity between two videos as the max correlation among all possible pairs in the two bags of features. On the official 5,000 video-pairs of the YouTube Face dataset for face verification, our algorithm achieves a comparable performance with VGG-face that averages over deep features of all frames. Other vision tasks can also benefit from the generic idea of employing geometric cues to improve the descriptiveness of deep features.

cs.CV↗

arXiv2016

Collaborative Multi-sensor Classification via Sparsity-based Representation

In this paper, we propose a general collaborative sparse representation framework for multi-sensor classification, which takes into account the correlations as well as complementary information between heterogeneous sensors simultaneously while considering joint sparsity within each sensor's observations. We also robustify our models to deal with the presence of sparse noise and low-rank interference signals. Specifically, we demonstrate that incorporating the noise or interference signal as a low-rank component in our models is essential in a multi-sensor classification problem when multiple co-located sources/sensors simultaneously record the same physical event. We further extend our frameworks to kernelized models which rely on sparsely representing a test sample in terms of all the training samples in a feature space induced by a kernel function. A fast and efficient algorithm based on alternative direction method is proposed where its convergence to an optimal solution is guaranteed. Extensive experiments are conducted on several real multi-sensor data sets and results are compared with the conventional classifiers to verify the effectiveness of the proposed methods.

cs.CV↗

arXiv2016

Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference

In this paper, we propose a burnscar detection model for hyperspectral imaging (HSI) data. The proposed model contains two-processing steps in which the first step separate and then suppress the cloud information presenting in the data set using an RPCA algorithm and the second step detect the burnscar area in the low-rank component output of the first step. Experiments are conducted on the public MODIS dataset available at NASA official website.

cs.CV↗

arXiv2015

Sparse Coding with Fast Image Alignment via Large Displacement Optical Flow

Sparse representation-based classifiers have shown outstanding accuracy and robustness in image classification tasks even with the presence of intense noise and occlusion. However, it has been discovered that the performance degrades significantly either when test image is not aligned with the dictionary atoms or the dictionary atoms themselves are not aligned with each other, in which cases the sparse linear representation assumption fails. In this paper, having both training and test images misaligned, we introduce a novel sparse coding framework that is able to efficiently adapt the dictionary atoms to the test image via large displacement optical flow. In the proposed algorithm, every dictionary atom is automatically aligned with the input image and the sparse code is then recovered using the adapted dictionary atoms. A corresponding supervised dictionary learning algorithm is also developed for the proposed framework. Experimental results on digit datasets recognition verify the efficacy and robustness of the proposed algorithm.

cs.CV↗

arXiv2015

Hierarchical Sparse and Collaborative Low-Rank Representation for Emotion Recognition

In this paper, we design a Collaborative-Hierarchical Sparse and Low-Rank (C-HiSLR) model that is natural for recognizing human emotion in visual data. Previous attempts require explicit expression components, which are often unavailable and difficult to recover. Instead, our model exploits the lowrank property over expressive facial frames and rescue inexact sparse representations by incorporating group sparsity. For the CK+ dataset, C-HiSLR on raw expressive faces performs as competitive as the Sparse Representation based Classification (SRC) applied on manually prepared emotions. C-HiSLR performs even better than SRC in terms of true positive rate.

cs.CV↗

arXiv2015

ICR: Iterative Convex Refinement for Sparse Signal Recovery Using Spike and Slab Priors

In this letter, we address sparse signal recovery using spike and slab priors. In particular, we focus on a Bayesian framework where sparsity is enforced on reconstruction coefficients via probabilistic priors. The optimization resulting from spike and slab prior maximization is known to be a hard non-convex problem, and existing solutions involve simplifying assumptions and/or relaxations. We propose an approach called Iterative Convex Refinement (ICR) that aims to solve the aforementioned optimization problem directly allowing for greater generality in the sparse structure. Essentially, ICR solves a sequence of convex optimization problems such that sequence of solutions converges to a sub-optimal solution of the original hard optimization problem. We propose two versions of our algorithm: a.) an unconstrained version, and b.) with a non-negativity constraint on sparse coefficients, which may be required in some real-world problems. Experimental validation is performed on both synthetic data and for a real-world image recovery problem, which illustrates merits of ICR over state of the art alternatives.

stat.ML↗

arXiv2015

Tensor sparsification via a bound on the spectral norm of random tensors

Given an order-$d$ tensor $\tensor A \in \R^{n \times n \times...\times n}$, we present a simple, element-wise sparsification algorithm that zeroes out all sufficiently small elements of $\tensor A$, keeps all sufficiently large elements of $\tensor A$, and retains some of the remaining elements with probabilities proportional to the square of their magnitudes. We analyze the approximation accuracy of the proposed algorithm using a powerful inequality that we derive. This inequality bounds the spectral norm of a random tensor and is of independent interest. As a result, we obtain novel bounds for the tensor sparsification problem.

math.NA↗

arXiv2015

Task-Driven Dictionary Learning for Hyperspectral Image Classification with Structured Sparsity Constraints

Sparse representation models a signal as a linear combination of a small number of dictionary atoms. As a generative model, it requires the dictionary to be highly redundant in order to ensure both a stable high sparsity level and a low reconstruction error for the signal. However, in practice, this requirement is usually impaired by the lack of labelled training samples. Fortunately, previous research has shown that the requirement for a redundant dictionary can be less rigorous if simultaneous sparse approximation is employed, which can be carried out by enforcing various structured sparsity constraints on the sparse codes of the neighboring pixels. In addition, numerous works have shown that applying a variety of dictionary learning methods for the sparse representation model can also improve the classification performance. In this paper, we highlight the task-driven dictionary learning algorithm, which is a general framework for the supervised dictionary learning method. We propose to enforce structured sparsity priors on the task-driven dictionary learning method in order to improve the performance of the hyperspectral classification. Our approach is able to benefit from both the advantages of the simultaneous sparse representation and those of the supervised dictionary learning. We enforce two different structured sparsity priors, the joint and Laplacian sparsity, on the task-driven dictionary learning method and provide the details of the corresponding optimization algorithms. Experiments on numerous popular hyperspectral images demonstrate that the classification performance of our approach is superior to sparse representation classifier with structured priors or the task-driven dictionary learning method.

cs.CV↗

arXiv2014

Structured Dictionary Learning for Classification

Sparsity driven signal processing has gained tremendous popularity in the last decade. At its core, the assumption is that the signal of interest is sparse with respect to either a fixed transformation or a signal dependent dictionary. To better capture the data characteristics, various dictionary learning methods have been proposed for both reconstruction and classification tasks. For classification particularly, most approaches proposed so far have focused on designing explicit constraints on the sparse code to improve classification accuracy while simply adopting $l_0$-norm or $l_1$-norm for sparsity regularization. Motivated by the success of structured sparsity in the area of Compressed Sensing, we propose a structured dictionary learning framework (StructDL) that incorporates the structure information on both group and task levels in the learning process. Its benefits are two-fold: (i) the label consistency between dictionary atoms and training data are implicitly enforced; and (ii) the classification performance is more robust in the cases of a small dictionary size or limited training data than other techniques. Using the subspace model, we derive the conditions for StructDL to guarantee the performance and show theoretically that StructDL is superior to $l_0$-norm or $l_1$-norm regularized dictionary learning for classification. Extensive experiments have been performed on both synthetic simulations and real world applications, such as face recognition and object classification, to demonstrate the validity of the proposed DL framework.

cs.CV↗

arXiv2014

Structured Priors for Sparse-Representation-Based Hyperspectral Image Classification

Pixel-wise classification, where each pixel is assigned to a predefined class, is one of the most important procedures in hyperspectral image (HSI) analysis. By representing a test pixel as a linear combination of a small subset of labeled pixels, a sparse representation classifier (SRC) gives rather plausible results compared with that of traditional classifiers such as the support vector machine (SVM). Recently, by incorporating additional structured sparsity priors, the second generation SRCs have appeared in the literature and are reported to further improve the performance of HSI. These priors are based on exploiting the spatial dependencies between the neighboring pixels, the inherent structure of the dictionary, or both. In this paper, we review and compare several structured priors for sparse-representation-based HSI classification. We also propose a new structured prior called the low rank group prior, which can be considered as a modification of the low rank prior. Furthermore, we will investigate how different structured priors improve the result for the HSI classification.

cs.CV↗

arXiv2011

Robust Lasso with missing and grossly corrupted observations

This paper studies the problem of accurately recovering a sparse vector $β^{\star}$ from highly corrupted linear measurements $y = X β^{\star} + e^{\star} + w$ where $e^{\star}$ is a sparse error vector whose nonzero entries may be unbounded and $w$ is a bounded noise. We propose a so-called extended Lasso optimization which takes into consideration sparse prior information of both $β^{\star}$ and $e^{\star}$. Our first result shows that the extended Lasso can faithfully recover both the regression as well as the corruption vector. Our analysis relies on the notion of extended restricted eigenvalue for the design matrix $X$. Our second set of results applies to a general class of Gaussian design matrix $X$ with i.i.d rows $\oper N(0, Σ)$, for which we can establish a surprising result: the extended Lasso can recover exact signed supports of both $β^{\star}$ and $e^{\star}$ from only $Ω(k \log p \log n)$ observations, even when the fraction of corruption is arbitrarily close to one. Our analysis also shows that this amount of observations required to achieve exact signed support is indeed optimal.

math.ST↗

arXiv2011

Discriminative Local Sparse Representations for Robust Face Recognition

A key recent advance in face recognition models a test face image as a sparse linear combination of a set of training face images. The resulting sparse representations have been shown to possess robustness against a variety of distortions like random pixel corruption, occlusion and disguise. This approach however makes the restrictive (in many scenarios) assumption that test faces must be perfectly aligned (or registered) to the training data prior to classification. In this paper, we propose a simple yet robust local block-based sparsity model, using adaptively-constructed dictionaries from local features in the training data, to overcome this misalignment problem. Our approach is inspired by human perception: we analyze a series of local discriminative features and combine them to arrive at the final classification decision. We propose a probabilistic graphical model framework to explicitly mine the conditional dependencies between these distinct sparse local features. In particular, we learn discriminative graphs on sparse representations obtained from distinct local slices of a face. Conditional correlations between these sparse features are first discovered (in the training phase), and subsequently exploited to bring about significant improvements in recognition rates. Experimental results obtained on benchmark face databases demonstrate the effectiveness of the proposed algorithms in the presence of multiple registration errors (such as translation, rotation, and scaling) as well as under variations of pose and illumination.

cs.CV↗

arXiv2011

Fast and Efficient Compressive Sensing using Structurally Random Matrices

This paper introduces a new framework of fast and efficient sensing matrices for practical compressive sensing, called Structurally Random Matrix (SRM). In the proposed framework, we pre-randomize a sensing signal by scrambling its samples or flipping its sample signs and then fast-transform the randomized samples and finally, subsample the transform coefficients as the final sensing measurements. SRM is highly relevant for large-scale, real-time compressive sensing applications as it has fast computation and supports block-based processing. In addition, we can show that SRM has theoretical sensing performance comparable with that of completely random sensing matrices. Numerical simulation results verify the validity of the theory as well as illustrate the promising potentials of the proposed sensing framework.

cs.IT↗