Real-world data processing problems often involve various image modalities associated with a certain scene, including RGB images, infrared images or multi-spectral images. The fact that different image modalities often share certain attributes, such as certain edges, textures and other structure primitives, represents an opportunity to enhance various image processing tasks. This paper proposes a new approach to construct a high-resolution (HR) version of a low-resolution (LR) image given another HR image modality as reference, based on joint sparse representations induced by coupled dictionaries. Our approach, which captures the similarities and disparities between different image modalities in a learned sparse feature domain in \emph{lieu} of the original image domain, consists of two phases. The coupled dictionary learning phase is used to learn a set of dictionaries that couple different image modalities in the sparse feature domain given a set of training data. In turn, the coupled super-resolution phase leverages such coupled dictionaries to construct a HR version of the LR target image given another related image modality. One of the merits of our sparsity-driven approach relates to the fact that it overcomes drawbacks such as the texture copying artifacts commonly resulting from inconsistency between the guidance and target images. Experiments on real multimodal images demonstrate that incorporating appropriate guidance information via joint sparse representation induced by coupled dictionary learning brings notable benefits in the super-resolution task with respect to the state-of-the-art. Of particular relevance, the proposed approach also demonstrates better robustness than competing deep-learning-based methods in the presence of noise.
Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The dictionaries and classification parameters are trained by a classification objective, and the sparse features are extracted by reducing a reconstruction loss in each layer. The reconstruction objectives in some sense regularize the classification problem and inject source signal information in the extracted features. The performance of the proposed hierarchical method increases by adding more layers, which consequently makes this model easier to tune and adapt. The proposed algorithm furthermore, shows remarkably lower fooling rate in presence of adversarial perturbation. The validation of the proposed approach is based on its classification performance using four benchmark datasets and is compared to a CNN of similar size.
Rectified linear units, or ReLUs, have become the preferred activation function for artificial neural networks. In this paper we consider two basic learning problems assuming that the underlying data follow a generative model based on a ReLU-network -- a neural network with ReLU activations. As a primarily theoretical study, we limit ourselves to a single-layer network. The first problem we study corresponds to dictionary-learning in the presence of nonlinearity (modeled by the ReLU functions). Given a set of observation vectors $\mathbf{y}^i \in \mathbb{R}^d, i =1, 2, \dots , n$, we aim to recover $d\times k$ matrix $A$ and the latent vectors $\{\mathbf{c}^i\} \subset \mathbb{R}^k$ under the model $\mathbf{y}^i = \mathrm{ReLU}(A\mathbf{c}^i +\mathbf{b})$, where $\mathbf{b}\in \mathbb{R}^d$ is a random bias. We show that it is possible to recover the column space of $A$ within an error of $O(d)$ (in Frobenius norm) under certain conditions on the probability distribution of $\mathbf{b}$. The second problem we consider is that of robust recovery of the signal in the presence of outliers, i.e., large but sparse noise. In this setting we are interested in recovering the latent vector $\mathbf{c}$ from its noisy nonlinear sketches of the form $\mathbf{v} = \mathrm{ReLU}(A\mathbf{c}) + \mathbf{e}+\mathbf{w}$, where $\mathbf{e} \in \mathbb{R}^d$ denotes the outliers with sparsity $s$ and $\mathbf{w} \in \mathbb{R}^d$ denote the dense but small noise. This line of work has recently been studied (Soltanolkotabi, 2017) without the presence of outliers. For this problem, we show that a generalized LASSO algorithm is able to recover the signal $\mathbf{c} \in \mathbb{R}^k$ within an $\ell_2$ error of $O(\sqrt{\frac{(k+s)\log d}{d}})$ when $A$ is a random Gaussian matrix.
This paper introduces a new nonlinear dictionary learning method for histograms in the probability simplex. The method leverages optimal transport theory, in the sense that our aim is to reconstruct histograms using so-called displacement interpolations (a.k.a. Wasserstein barycenters) between dictionary atoms; such atoms are themselves synthetic histograms in the probability simplex. Our method simultaneously estimates such atoms, and, for each datapoint, the vector of weights that can optimally reconstruct it as an optimal transport barycenter of such atoms. Our method is computationally tractable thanks to the addition of an entropic regularization to the usual optimal transportation problem, leading to an approximation scheme that is efficient, parallel and simple to differentiate. Both atoms and weights are learned using a gradient-based descent method. Gradients are obtained by automatic differentiation of the generalized Sinkhorn iterations that yield barycenters with entropic smoothing. Because of its formulation relying on Wasserstein barycenters instead of the usual matrix product between dictionary and codes, our method allows for nonlinear relationships between atoms and the reconstruction of input data. We illustrate its application in several different image processing settings.
Partial person re-identification (re-id) is a challenging problem, where only several partial observations (images) of people are available for matching. However, few studies have provided flexible solutions to identifying a person in an image containing arbitrary part of the body. In this paper, we propose a fast and accurate matching method to address this problem. The proposed method leverages Fully Convolutional Network (FCN) to generate fix-sized spatial feature maps such that pixel-level features are consistent. To match a pair of person images of different sizes, a novel method called Deep Spatial feature Reconstruction (DSR) is further developed to avoid explicit alignment. Specifically, DSR exploits the reconstructing error from popular dictionary learning models to calculate the similarity between different spatial feature maps. In that way, we expect that the proposed FCN can decrease the similarity of coupled images from different persons and increase that from the same person. Experimental results on two partial person datasets demonstrate the efficiency and effectiveness of the proposed method in comparison with several state-of-the-art partial person re-id approaches. Additionally, DSR achieves competitive results on a benchmark person dataset Market1501 with 83.58\% Rank-1 accuracy.
This paper addresses the problem of learning dictionaries for multimodal datasets, i.e. datasets collected from multiple data sources. We present an algorithm called multimodal sparse Bayesian dictionary learning (MSBDL). MSBDL leverages information from all available data modalities through a joint sparsity constraint. The underlying framework offers a considerable amount of flexibility to practitioners and addresses many of the shortcomings of existing multimodal dictionary learning approaches. In particular, the procedure includes the automatic tuning of hyperparameters and is unique in that it allows the dictionaries for each data modality to have different cardinality, a significant feature in cases when the dimensionality of data differs across modalities. MSBDL is scalable and can be used in supervised learning settings. Theoretical results relating to the convergence of MSBDL are presented and the numerical results provide evidence of the superior performance of MSBDL on synthetic and real datasets compared to existing methods.
The thresholded feature has recently emerged as an extremely efficient, yet rough empirical approximation, of the time-consuming sparse coding inference process. Such an approximation has not yet been rigorously examined, and standard dictionaries often lead to non-optimal performance when used for computing thresholded features. In this paper, we first present two theoretical recovery guarantees for the thresholded feature to exactly recover the nonzero support of the sparse code. Motivated by them, we then formulate the Dictionary Learning for Thresholded Features (DLTF) model, which learns an optimized dictionary for applying the thresholded feature. In particular, for the $(k, 2)$ norm involved, a novel proximal operator with log-linear time complexity $O(m\log m)$ is derived. We evaluate the performance of DLTF on a vast range of synthetic and real-data tasks, where DLTF demonstrates remarkable efficiency, effectiveness and robustness in all experiments. In addition, we briefly discuss the potential link between DLTF and deep learning building blocks.
Matrix factorization is a key tool in data analysis; its applications include recommender systems, correlation analysis, signal processing, among others. Binary matrices are a particular case which has received significant attention for over thirty years, especially within the field of data mining. Dictionary learning refers to a family of methods for learning overcomplete basis (also called frames) in order to efficiently encode samples of a given type; this area, now also about twenty years old, was mostly developed within the signal processing field. In this work we propose two binary matrix factorization methods based on a binary adaptation of the dictionary learning paradigm to binary matrices. The proposed algorithms focus on speed and scalability; they work with binary factors combined with bit-wise operations and a few auxiliary integer ones. Furthermore, the methods are readily applicable to online binary matrix factorization. Another important issue in matrix factorization is the choice of rank for the factors; we address this model selection problem with an efficient method based on the Minimum Description Length principle. Our preliminary results show that the proposed methods are effective at producing interpretable factorizations of various data types of different nature.
Diffusion magnetic resonance imaging, a non-invasive tool to infer white matter fiber connections, produces a large number of streamlines containing a wealth of information on structural connectivity. The size of these tractography outputs makes further analyses complex, creating a need for methods to group streamlines into meaningful bundles. In this work, we address this by proposing a set of kernel dictionary learning and sparsity priors based methods. Proposed frameworks include L-0 norm, group sparsity, as well as manifold regularization prior. The proposed methods allow streamlines to be assigned to more than one bundle, making it more robust to overlapping bundles and inter-subject variations. We evaluate the performance of our method on a labeled set and data from Human Connectome Project. Results highlight the ability of our method to group streamlines into plausible bundles and illustrate the impact of sparsity priors on the performance of the proposed methods.
In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this work, we propose a novel domain-adaptive dictionary learning framework for cross-domain visual recognition. Our method generates a set of intermediate domains. These intermediate domains form a smooth path and bridge the gap between the source and target domains. Specifically, we not only learn a common dictionary to encode the domain-shared features, but also learn a set of domain-specific dictionaries to model the domain shift. The separation of the common and domain-specific dictionaries enables us to learn more compact and reconstructive dictionaries for domain adaptation. These dictionaries are learned by alternating between domain-adaptive sparse coding and dictionary updating steps. Meanwhile, our approach gradually recovers the feature representations of both source and target data along the domain path. By aligning all the recovered domain data, we derive the final domain-adaptive features for cross-domain visual recognition. Extensive experiments on three public datasets demonstrates that our approach outperforms most state-of-the-art methods.
This paper studies the convergence behaviour of dictionary learning via the Iterative Thresholding and K-residual Means (ITKrM) algorithm. On one hand it is proved that ITKrM is a contraction under much more relaxed conditions than previously necessary. On the other hand it is shown that there seem to exist stable fixed points that do not correspond to the generating dictionary, which can be characterised as very coherent. Based on an analysis of the residuals using these bad dictionaries, replacing coherent atoms with carefully designed replacement candidates is proposed. In experiments on synthetic data this outperforms random or no replacement and always leads to full dictionary recovery. Finally the question how to learn dictionaries without knowledge of the correct dictionary size and sparsity level is addressed. Decoupling the replacement strategy of coherent or unused atoms into pruning and adding, and slowly carefully increasing the sparsity level, leads to an adaptive version of ITKrM. In several experiments this adaptive dictionary learning algorithm is shown to recover a generating dictionary from randomly initialised dictionaries of various sizes on synthetic data and to learn meaningful dictionaries on image data.
Among the representation learning, the low-rank representation (LRR) is one of the hot research topics in many fields, especially in image processing and pattern recognition. Although LRR can capture the global structure, the ability of local structure preservation is limited because LRR lacks dictionary learning. In this paper, we propose a novel multi-focus image fusion method based on dictionary learning and LRR to get a better performance in both global and local structure. Firstly, the source images are divided into several patches by sliding window technique. Then, the patches are classified according to the Histogram of Oriented Gradient (HOG) features. And the sub-dictionaries of each class are learned by K-singular value decomposition (K-SVD) algorithm. Secondly, a global dictionary is constructed by combining these sub-dictionaries. Then, we use the global dictionary in LRR to obtain the LRR coefficients vector for each patch. Finally, the l_1-norm and choose-max fuse strategy for each coefficients vector is adopted to reconstruct fused image from the fused LRR coefficients and the global dictionary. Experimental results demonstrate that the proposed method can obtain state-of-the-art performance in both qualitative and quantitative evaluations compared with serval classical methods and novel methods.The Code of our fusion method is available at https://github.com/hli1221/imagefusion_dllrr
Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such as hyper-spectral imaging or blood glucose monitoring), only an incomplete fraction of the data entries may be available. For incomplete settings, no provably correct and polynomial-time algorithm has been reported in the dictionary learning literature. In this paper, we provide provable approaches for learning - from incomplete samples - a family of dictionaries whose atoms have sufficiently "spread-out" mass. First, we propose a descent-style iterative algorithm that linearly converges to the true dictionary when provided a sufficiently coarse initial estimate. Second, we propose an initialization algorithm that utilizes a small number of extra fully observed samples to produce such a coarse initial estimate. Finally, we theoretically analyze their performance and provide asymptotic statistical and computational guarantees.
Light field imaging is a rich way of representing the 3D world around us. However, due to limited sensor resolution capturing light field data inherently poses spatio-angular resolution trade-off. In this paper, we propose a deep learning based solution to tackle the resolution trade-off. Specifically, we reconstruct full sensor resolution light field from a single coded image. We propose to do this in three stages 1) reconstruction of center view from the coded image 2) estimating disparity map from the coded image and center view 3) warping center view using the disparity to generate light field. We propose three neural networks for these stages. Our disparity estimation network is trained in an unsupervised manner alleviating the need for ground truth disparity. Our results demonstrate better recovery of parallax from the coded image. Also, we get better results than dictionary learning based approaches both qualitatively and quatitatively.
In this paper we show that the computational complexity of the Iterative Thresholding and K-residual-Means (ITKrM) algorithm for dictionary learning can be significantly reduced by using dimensionality-reduction techniques based on the Johnson-Lindenstrauss lemma. The dimensionality reduction is efficiently carried out with the fast Fourier transform. We introduce the Iterative compressed-Thresholding and K-Means (IcTKM) algorithm for fast dictionary learning and study its convergence properties. We show that IcTKM can locally recover an incoherent, overcomplete generating dictionary of $K$ atoms from training signals of sparsity level $S$ with high probability. Fast dictionary learning is achieved by embedding the training data and the dictionary into $m < d$ dimensions, and recovery is shown to be locally stable with an embedding dimension which scales as low as $m = O(S \log^4 S \log^3 K)$. The compression effectively shatters the data dimension bottleneck in the computational cost of ITKrM, reducing it by a factor $O(m/d)$. Our theoretical results are complemented with numerical simulations which demonstrate that IcTKM is a powerful, low-cost algorithm for learning dictionaries from high-dimensional data sets.
We propose a computationally efficient and high-performance classification algorithm by incorporating class structural information in analysis dictionary learning. To achieve more consistent classification, we associate a class characteristic structure of independent subspaces and impose it on the classification error constrained analysis dictionary learning. Experiments demonstrate that our method achieves a comparable or better performance than the state-of-the-art algorithms in a variety of visual classification tasks. In addition, our method greatly reduces the training and testing computational complexity.
In this paper, we propose a novel information theoretic framework for dictionary learning (DL) and sparse coding (SC) on a statistical manifold (the manifold of probability distributions). Unlike the traditional DL and SC framework, our new formulation does not explicitly incorporate any sparsity inducing norm in the cost function being optimized but yet yields sparse codes. Our algorithm approximates the data points on the statistical manifold (which are probability distributions) by the weighted Kullback-Leibeler center/mean (KL-center) of the dictionary atoms. The KL-center is defined as the minimizer of the maximum KL-divergence between itself and members of the set whose center is being sought. Further, we prove that the weighted KL-center is a sparse combination of the dictionary atoms. This result also holds for the case when the KL-divergence is replaced by the well known Hellinger distance. From an applications perspective, we present an extension of the aforementioned framework to the manifold of symmetric positive definite matrices (which can be identified with the manifold of zero mean gaussian distributions), $\mathcal{P}_n$. We present experiments involving a variety of dictionary-based reconstruction and classification problems in Computer Vision. Performance of the proposed algorithm is demonstrated by comparing it to several state-of-the-art methods in terms of reconstruction and classification accuracy as well as sparsity of the chosen representation.
Sparse representation leads to an efficient way to approximately recover a signal by the linear composition of a few bases from a learnt dictionary, based on which various successful applications have been achieved. However, in the scenario of data compression, its efficiency and popularity are hindered. It is because of the fact that encoding sparsely distributed coefficients may consume more bits for representing the index of nonzero coefficients. Therefore, introducing an accurate rate-constraint in sparse coding and dictionary learning becomes meaningful, which has not been fully exploited in the context of sparse representation. According to the Shannon entropy inequality, the variance of a Gaussian distributed data bounds its entropy, indicating the actual bitrate can be well estimated by its variance. Hence, a Globally Variance-Constrained Sparse Representation (GVCSR) model is proposed in this work, where a variance-constrained rate term is introduced to the optimization process. Specifically, we employ the Alternating Direction Method of Multipliers (ADMM) to solve the non-convex optimization problem for sparse coding and dictionary learning, both of them have shown the state-of-the-art rate-distortion performance for image representation. Furthermore, we investigate the potential of applying the GVCSR algorithm in the practical image set compression, where the optimized dictionary is trained to efficiently represent the images captured in similar scenarios by implicitly utilizing inter-image correlations. Experimental results have demonstrated superior rate-distortion performance against the state-of-the-art methods.
Dictionary learning is a popular approach for inferring a hidden basis or dictionary in which data has a sparse representation. Data generated from the dictionary A (an n by m matrix, with m > n in the over-complete setting) is given by Y = AX where X is a matrix whose columns have supports chosen from a distribution over k-sparse vectors, and the non-zero values chosen from a symmetric distribution. Given Y, the goal is to recover A and X in polynomial time. Existing algorithms give polytime guarantees for recovering incoherent dictionaries, under strong distributional assumptions both on the supports of the columns of X, and on the values of the non-zero entries. In this work, we study the following question: Can we design efficient algorithms for recovering dictionaries when the supports of the columns of X are arbitrary? To address this question while circumventing the issue of non-identifiability, we study a natural semirandom model for dictionary learning where there are a large number of samples $y=Ax$ with arbitrary k-sparse supports for x, along with a few samples where the sparse supports are chosen uniformly at random. While the few samples with random supports ensures identifiability, the support distribution can look almost arbitrary in aggregate. Hence existing algorithmic techniques seem to break down as they make strong assumptions on the supports. Our main contribution is a new polynomial time algorithm for learning incoherent over-complete dictionaries that works under the semirandom model. Additionally the same algorithm provides polynomial time guarantees in new parameter regimes when the supports are fully random. Finally using these techniques, we also identify a minimal set of conditions on the supports under which the dictionary can be (information theoretically) recovered from polynomial samples for almost linear sparsity, i.e., $k=\tilde{O}(n)$.
Learning optimal dictionaries for sparse coding has exposed characteristic sparse features of many natural signals. However, universal guarantees of the stability of such features in the presence of noise are lacking. Here, we provide very general conditions guaranteeing when dictionaries yielding the sparsest encodings are unique and stable with respect to measurement or modeling error. We demonstrate that some or all original dictionary elements are recoverable from noisy data even if the dictionary fails to satisfy the spark condition, its size is overestimated, or only a polynomial number of distinct sparse supports appear in the data. Importantly, we derive these guarantees without requiring any constraints on the recovered dictionary beyond a natural upper bound on its size. Our results also yield an effective procedure sufficient to affirm if a proposed solution to the dictionary learning problem is unique within bounds commensurate with the noise. We suggest applications to data analysis, engineering, and neuroscience and close with some remaining challenges left open by our work.