Sparse Coding Techniques Research Articles

A Deep Unfolding Network for Multispectral and Hyperspectral Image Fusion

Multispectral and hyperspectral image fusion (MS/HS fusion) aims to generate a high-resolution hyperspectral (HRHS) image by fusing a high-resolution multispectral (HRMS) and a low-resolution hyperspectral (LRHS) images. The deep unfolding-based MS/HS fusion method is a representative deep learning paradigm due to its excellent performance and sufficient interpretability. However, existing deep unfolding-based MS/HS fusion methods only rely on a fixed linear degradation model, which focuses on modeling the relationships between HRHS and HRMS, as well as HRHS and LRHS. In this paper, we break free from this observation model framework and propose a new observation model. Firstly, the proposed observation model is built based on the convolutional sparse coding (CSC) technique, and then a proximal gradient algorithm is designed to solve this model. Secondly, we unfold the iterative algorithm into a deep network, dubbed as MHF-CSCNet, where the proximal operators are learned using convolutional neural networks. Finally, all trainable parameters can be automatically learned end-to-end from the training pairs. Experimental evaluations conducted on various benchmark datasets demonstrate the superiority of our method both quantitatively and qualitatively compared to other state-of-the-art methods.

Improved multi-focus image fusion using online convolutional sparse coding based on sample-dependent dictionary

Multi-focus image fusion merges multiple images captured from different focused regions of a scene to create a fully-focused image. Convolutional sparse coding (CSC) methods are commonly employed for accurate extraction of focused regions, but they often disregard computational costs. To overcome this, an online convolutional sparse coding (OCSC) technique was introduced, but its performance is still limited by the number of filters used, affecting overall performance negatively. To address these limitations, a novel approach called Sample-Dependent Dictionary-based Online Convolutional Sparse Coding (SCSC) was proposed. SCSC enables the utilization of additional filters while maintaining low time and space complexity for processing high-dimensional or large data. Leveraging the computational efficiency and effective global feature extraction of SCSC, we propose a novel method for multi-focus image fusion. Our method involves a two-layer decomposition of each source image, yielding a base layer capturing the predominant features and a detail layer containing finer details. The amalgamation of the fused base and detail layers culminates in the reconstruction of the final image. The proposed method significantly mitigates artifacts, preserves fine details at the focus boundary, and demonstrates notable enhancements in both visual quality and objective evaluation of multi-focus image fusion.

Bayesian sparsity and class sparsity priors for dictionary learning and coding

Dictionary learning methods continue to gain popularity for the solution of challenging inverse problems. In the dictionary learning approach, the computational forward model is replaced by a large dictionary of possible outcomes, and the problem is to identify the dictionary entries that best match the data, akin to traditional query matching in search engines. Sparse coding techniques are used to guarantee that the dictionary matching identifies only few of the dictionary entries, and dictionary compression methods are used to reduce the complexity of the matching problem. In this article, we propose a work flow to facilitate the dictionary matching process. First, the full dictionary is divided into subdictionaries that are separately compressed. The error introduced by the dictionary compression is handled in the Bayesian framework as a modeling error. Furthermore, we propose a new Bayesian data-driven group sparsity coding method to help identify subdictionaries that are not relevant for the dictionary matching. After discarding irrelevant subdictionaries, the dictionary matching is addressed as a deflated problem using sparse coding. The compression and deflation steps can lead to substantial decreases of the computational complexity. The effectiveness of compensating for the dictionary compression error and using the novel group sparsity promotion to deflate the original dictionary are illustrated by applying the methodology to real world problems, the glitch detection in the LIGO experiment and hyperspectral remote sensing.

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI

Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue microstructure based on biophysical models, which are typically multi-compartmental models with mathematically complex and highly non-linear forms. Resolving microstructures from these models with conventional optimization techniques is prone to estimation errors and requires dense sampling in the q-space with a long scan time. Deep learning based approaches have been proposed to overcome these limitations. Motivated by the superior performance of the Transformer in feature extraction than the convolutional structure, in this work, we present a learning-based framework based on Transformer, namely, a Microstructure Estimation Transformer with Sparse Coding (METSC) for dMRI-based microstructural parameter estimation. To take advantage of the Transformer while addressing its limitation in large training data requirement, we explicitly introduce an inductive bias-model bias into the Transformer using a sparse coding technique to facilitate the training process. Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage. The embedding stage is a Transformer-based structure that encodes the signal in a high-level space to ensure the core voxel of a patch is represented effectively. In the sparse representation stage, a dictionary is constructed by solving a sparse reconstruction problem that unfolds the Iterative Hard Thresholding (IHT) process. The mapping stage is essentially a decoder that computes the microstructural parameters from the output of the second stage, based on the weighted sum of normalized dictionary coefficients where the weights are also learned. We tested our framework on two dMRI models with downsampled q-space data, including the intravoxel incoherent motion (IVIM) model and the neurite orientation dispersion and density imaging (NODDI) model. The proposed method achieved up to 11.25 folds of acceleration while retaining high fitting accuracy for NODDI fitting, reducing the mean squared error (MSE) up to 70% compared with the previous q-space learning approach. METSC outperformed the other state-of-the-art learning-based methods, including the model-free and model-based methods. The network also showed robustness against noise and generalizability across different datasets. The superior performance of METSC indicates its potential to improve dMRI acquisition and model fitting in clinical applications.

Proximal PanNet: A Model-Based Deep Network for Pansharpening

Recently, deep learning techniques have been extensively studied for pansharpening, which aims to generate a high resolution multispectral (HRMS) image by fusing a low resolution multispectral (LRMS) image with a high resolution panchromatic (PAN) image. However, existing deep learning-based pansharpening methods directly learn the mapping from LRMS and PAN to HRMS. These network architectures always lack sufficient interpretability, which limits further performance improvements. To alleviate this issue, we propose a novel deep network for pansharpening by combining the model-based methodology with the deep learning method. Firstly, we build an observation model for pansharpening using the convolutional sparse coding (CSC) technique and design a proximal gradient algorithm to solve this model. Secondly, we unfold the iterative algorithm into a deep network, dubbed as Proximal PanNet, by learning the proximal operators using convolutional neural networks. Finally, all the learnable modules can be automatically learned in an end-to-end manner. Experimental results on some benchmark datasets show that our network performs better than other advanced methods both quantitatively and qualitatively.

Sparse-Coding-Based Autoencoder and Its Application for Cancer Survivability Prediction

Cancer-survivability prediction is one of the popular research topics, that attracted great attention from both the health service providers and academia. However, one remaining question comes from how to make full use of a large number of available factors (or features). This paper, accordingly, presents a novel autoencoder algorithm based on the concept of sparse coding to address this problem. The main contribution is twofold: the utilization of sparsity coding for input feature selection and a subsequent classification using latent information. Precisely, a typical autoencoder architecture is employed for reconstructing the original input. Then the sparse coding technique is applied to optimize the network structure, with the aim of selecting optimal features and enhancing the generalization capability. In addition, the refined latent information is further cast as alternative features for training a sparse classifier. To evaluate the performance of the proposed autoencoder architecture, we present a comprehensive analysis using a publicly available data repository (i.e., Surveillance, Epidemiology, and End Results, SEER). Experimental study shows that the proposed approach has the ability of extracting important features from high-dimensional inputs and achieves competitive performance than other state-of-the-art classification techniques.

Uncovering Statistical Links Between Gene Expression and Structural Connectivity Patterns in the Mouse Brain

Finding links between genes and structural connectivity is of the utmost importance for unravelling the underlying mechanism of the brain connectome. In this study we identify links between the gene expression and the axonal projection density in the mouse brain, by applying a modified version of the Linked ICA method to volumetric data from the Allen Institute for Brain Science for identifying independent sources of information that link both modalities at the voxel level. We performed separate analyses on sets of projections from the visual cortex, the caudoputamen and the midbrain reticular nucleus, and we determined those brain areas, injections and genes that were most involved in independent components that link both gene expression and projection density data, while we validated their biological context through enrichment analysis. We identified representative and literature-validated cortico-midbrain and cortico-striatal projections, whose gene subsets were enriched with annotations for neuronal and synaptic function and related developmental and metabolic processes. The results were highly reproducible when including all available projections, as well as consistent with factorisations obtained using the Dictionary Learning and Sparse Coding technique. Hence, Linked ICA yielded reproducible independent components that were preserved under increasing data variance. Taken together, we have developed and validated a novel paradigm for linking gene expression and structural projection patterns in the mouse mesoconnectome, which can power future studies aiming to relate genes to brain function.

Overcoming Catastrophic Forgetting Using Sparse Coding and Meta Learning

Continuous learning occurs naturally in human beings. However, Deep Learning methods suffer from a problem known as Catastrophic Forgetting (CF) that consists of a model drastically decreasing its performance on previously learned tasks when it is sequentially trained on new tasks. This situation, known as task interference, occurs when a network modifies relevant weight values as it learns a new task. In this work, we propose two main strategies to face the problem of task interference in convolutional neural networks. First, we use a sparse coding technique to adaptively allocate model capacity to different tasks avoiding interference between them. Specifically, we use a strategy based on group sparse regularization to specialize groups of parameters to learn each task. Afterward, by adding binary masks, we can freeze these groups of parameters, using the rest of the network to learn new tasks. Second, we use a meta learning technique to foster knowledge transfer among tasks, encouraging weight reusability instead of overwriting. Specifically, we use an optimization strategy based on episodic training to foster learning weights that are expected to be useful to solve future tasks. Together, these two strategies help us to avoid interference by preserving compatibility with previous and future weight values. Using this approach, we achieve state-of-the-art results on popular benchmarks used to test techniques to avoid CF. In particular, we conduct an ablation study to identify the contribution of each component of the proposed method, demonstrating its ability to avoid retroactive interference with previous tasks and to promote knowledge transfer to future tasks.

Fault Detection and Behavior Analysis of Wheelset Bearing Using Adaptive Convolutional Sparse Coding Technique Combined with Bandwidth Optimization

Wheelset bearing is a critical and easily damaged component of a high-speed train. Wheelset bearing fault diagnosis is of great significance to ensure safe operation of high-speed trains and realize intelligent operation and maintenance. The convolutional sparse coding technique based on the dictionary learning algorithm (CSCT-DLA) provides an effective algorithm framework for extracting the impulses caused by bearing defect. However, dictionary learning is easily affected by foundation vibration and harmonic interference and cannot learn the key structure related to fault impulses. At the same time, the detection performance of fault impulse heavily depends on the selection of parameters in this approach. Union of convolutional dictionary learning algorithm (UC-DLA) is an efficient algorithm in CSCT-DLA. In this paper, UC-DLA is introduced and improved for wheelset bearing fault detection. Finally, a novel bearing fault detection method, adaptive UC-DLA combined with bandwidth optimization (AUC-DLA-BO), is proposed. The mathematical formulation of AUC-DLA-BO is a sort of constrained optimization problem, which can overcome foundation vibration and harmonic interference and adaptively determine parameters related to UC-DLA. The proposed method can detect the fault resonance band adaptively, eliminate the noise with the same frequency band as the fault resonance band, and highlight the bearing fault impulses. Simulated signals and bench tests are used to verify the effectiveness of the proposed method. The results show that AUC-DLA-BO can effectively detect bearing faults and realize the refined analysis of fault behavior.

Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification

Effective management of chronic constrictive pulmonary conditions lies in proper and timely administration of medication. As a series of studies indicates, medication adherence can effectively be monitored by successfully identifying actions performed by patients during inhaler usage. This study focuses on the recognition of inhaler audio events during usage of pressurized metered dose inhalers (pMDI). Aiming at real-time performance, we investigate deep sparse coding techniques including convolutional filter pruning, scalar pruning and vector quantization, for different convolutional neural network (CNN) architectures. The recognition performance has been assessed on three healthy subjects following both within and across subjects modeling strategies. The selected CNN architecture classified drug actuation, inhalation and exhalation events, with 100%, 92.6% and 97.9% accuracy, respectively, when assessed in a leave-one-subject-out cross-validation setting. Moreover, sparse coding of the same architecture with an increasing compression rate from 1 to 7 resulted in only a small decrease in classification accuracy (from 95.7% to 94.5%), obtained by random (subject-agnostic) cross-validation. A more thorough assessment on a larger dataset, including recordings of subjects with multiple respiratory disease manifestations, is still required in order to better evaluate the method’s generalization ability and robustness.

Binning unassembled short reads based on k-mer abundance covariance using sparse coding.

BackgroundSequence-binning techniques enable the recovery of an increasing number of genomes from complex microbial metagenomes and typically require prior metagenome assembly, incurring the computational cost and drawbacks of the latter, e.g., biases against low-abundance genomes and inability to conveniently assemble multi-terabyte datasets.ResultsWe present here a scalable pre-assembly binning scheme (i.e., operating on unassembled short reads) enabling latent genome recovery by leveraging sparse dictionary learning and elastic-net regularization, and its use to recover hundreds of metagenome-assembled genomes, including very low-abundance genomes, from a joint analysis of microbiomes from the LifeLines DEEP population cohort (n = 1,135, >1010 reads).ConclusionWe showed that sparse coding techniques can be leveraged to carry out read-level binning at large scale and that, despite lower genome reconstruction yields compared to assembly-based approaches, bin-first strategies can complement the more widely used assembly-first protocols by targeting distinct genome segregation profiles. Read enrichment levels across 6 orders of magnitude in relative abundance were observed, indicating that the method has the power to recover genomes consistently segregating at low levels.

Semi‐supervised uncorrelated dictionary learning for colour face recognition

Colour images are increasingly used in the fields of computer vision, pattern recognition and machine learning, since they can provide more identifiable information than greyscale images. Thus, colour face recognition has attracted accumulating attention. Its key problem is how to remove the similarity between colour component images and take full advantage of colour difference information. Decision‐level similarity reduction between colour component images directly affects the recognition effect, but it has been found in no work. In this study, the authors propose a novel colour face recognition approach named semi‐supervised uncorrelated dictionary learning (SUDL), which realises decision‐level similarity reduction and fusion of all colour components in face images. SUDL employs the labelled and unlabelled colour face image samples into structured dictionary learning to achieve three uncorrelated discriminating dictionaries corresponding to three colour components of face images, and then uses these dictionaries and the sparse coding technique to make a classification decision. Experimental results in multiple public colour face image databases demonstrate that the dictionary decorrelation, structured dictionary learning and unlabelled samples used in the proposed approach are effective and reasonable, and the proposed approach outperforms several representative colour face recognition methods in recognition rates, despite of its poor time performance.

Food-texture dimensions expressed by Japanese onomatopoeic words.

This study examined perceptual dimensions of food texture using Japanese onomatopoeic words. Photographs of 56 foods were presented to the participants, and they reported onomatopoeic (mimetic) words suitable for the texture of the foods. The participants' responses were collated into a contingency table of photographs by onomatopoeic words. Correspondence analysis was applied to the table, and 15 dimensions were extracted. The biplot of the configurations was rotated by the technique of sparse coding. The obtained dimensions were smoothness/sounds in slurping noodles; adhesiveness; crumbliness/dryness/fluffiness of breads; popping/juiciness of spherical‐shaped foods; soft elasticity/smoothness of gel, wateriness/creaminess; bendability of sticky foods; crispness/crunchiness of snacks; crispness of fruits; elasticity; crunchiness of vegetables; breakability of rod‐like foods; sizzle (high temperature and oiliness); and two dimensions specifically expressing textures of lemon and pickled plum. These are considered to be basic food‐texture dimensions expressed by Japanese onomatopoeic words.

Learning Structured Sparse Representations for Voice Conversion

Sparse-coding techniques for voice conversion assume that an utterance can be decomposed into a sparse code that only carries linguistic contents, and a dictionary of atoms that captures the speakers’ characteristics. However, conventional dictionary-construction and sparse-coding algorithms rarely meet this assumption. The result is that the sparse code is no longer speaker-independent, which leads to lower voice-conversion performance. In this paper, we propose a Cluster-Structured Sparse Representation (CSSR) that improves the speaker independence of the representations. CSSR consists of two complementary components: a Cluster-Structured Dictionary Learning module that groups atoms in the dictionary into clusters, and a Cluster-Selective Objective Function that encourages each speech frame to be represented by atoms from a small number of clusters. We conducted four experiments on the CMU ARCTIC corpus to evaluate the proposed method. In a first ablation study, results show that each of the two CSSR components enhances speaker independence, and that combining both components leads to further improvements. In a second experiment, we find that CSSR uses increasingly larger dictionaries more efficiently than phoneme-based representations by allowing finer-grained decompositions of speech sounds. In a third experiment, results from objective and subjective measurements show that CSSR outperforms prior voice-conversion methods, improving the acoustic quality of the synthesized speech while retaining the target speaker's voice identity. Finally, we show that the CSSR captures latent (i.e., phonetic) information in the speech signal.

Vegetation High-Impedance Faults’ High-Frequency Signatures via Sparse Coding

High-impedance faults (HIFs) behavior in power distribution systems depends on multiple factors, making it a challenging disturbance to model. Factors, such as network characteristics and impedance surface, can change the phenomena so intensely that insights about their behavior may not translate well between faults with different parameters. Signal processing techniques can help reveal patterns from specific types of fault, given the availability of sampled data from real faults. The methodology described in this article uses the shift-invariant sparse coding technique on a data set of staged vegetation HIFs to address this hypothesis. The technique facilitates the uncoupling of shifted and convoluted patterns present in the recorded fault signals, while a methodology to correlate them with fault occurrences is proposed. The investigation of underdiscussed high-frequency fault signals from a specific type of fault (small current vegetation HIFs) distinguishes this article from related works. The methodology to attest the found patterns as fault signatures and their analysis while using a particular high-frequency sampling method are key novel aspects presented. Nonetheless, the evidence of consistent behavior in real vegetation HIFs at higher frequencies that could assist their detection is the main contribution of this article. These results can enhance phenomena awareness and support future methodologies dealing with such disturbances.

Semi-Supervised Graph Based Embedding With Non-Convex Sparse Coding Techniques

We consider the problem of semi-supervised graph-based learning upon multimodal and mixmodal data. Since in semi-supervised settings, the labeled information is very limited, we first propose a non-convex sparse-coding based label propagation ( $\alpha$ α -SLP) method to estimate the soft labels, and thereby to enrich the supervised information. By considering the structural properties of multimodal and mixmodal data, we present a semi-supervised graph-based embedding (SGE) approach that incorporates the soft label information with the hierarchical local geometric information of within-class, between-class, and overall-class data. Based on this, subspaces characterizing the multimodal and mixmodal data structure can be derived by maximizing the weighted between-class separability and minimizing the locality-preserved within-class as well as overall-class distances of the training samples. We further extend SGE into semi-supervised sparse subspace learning scenarios and present an $\alpha$ α -structural-regularization-induced SGE ( $\alpha$ α -SSGE) model, which can give better results in extracting discriminative groups of features by utilizing the non-convex structural regularization techniques. Experiments for multimodal and mixmodal digit as well as face recognition verify the validity and effectiveness of the proposed models.

Performance Improvement of Hand Gesture Recognition By using Sparse Coding With Kinect V2 Sensors

This paper presents an important technique with improvement property for image identification intention. Here the important technique which is sparse coding representation acts as a major ROLE in achiveving One-short learning and real recognition of actions[1]. The implementation method based on mainly 3-D Histogram of prospect flow with Global Histograms of orientated Gradient .The major and most important of this method is to use imprison on major level regions from the given data sets . With this data then suggest a instantaneous to get video segmentation and video gratitude of hand gesture action by using linear SVMs.This paper mainly highlights the major role of sparse coding technique to stand for 3D proceedings [2] .From this paper we obtain very good results in an domestic dataset captured by Kinect V2 sensors together with hand gesture proceedings and complex hand gesture actions differing by small details.

Vision‐based traffic accident detection using sparse spatio‐temporal features and weighted extreme learning machine

Vision-based traffic accident detection is one of the challenging tasks in intelligent transportation systems due to the multi-modalities of traffic accidents. The first challenging issue is about how to learn robust and discriminative spatio-temporal feature representations. Since few training samples of traffic accidents can be collected, sparse coding techniques can be used for small data case. However, most sparse coding algorithms which use norm regularisation may not achieve enough sparsity. The second challenging issue is about the sample imbalance between traffic accidents and normal traffic such that detector would like to favour normal traffic. This study proposes a traffic accident detection method, including a self-tuning iterative hard thresholding (ST-IHT) algorithm for learning sparse spatio-temporal features and a weighted extreme learning machine (W-ELM) for detection. The ST-IHT algorithm can improve the sparsity of encoded features by solving an norm regularisation. The W-ELM can put more focus on traffic accident samples. Meanwhile, a two-point search strategy is proposed to adaptively find a candidate value of Lipschitz coefficients to improve the tuning precision. Experimental results in our collected dataset have shown that this proposed traffic accident detection algorithm outperforms other state-of-the-art methods in terms of the feature's sparsity and detection performance.

Correlation-Weighted Sparse Representation for Robust Liver DCE-MRI Decomposition Registration.

Conducting an accurate motion correction of liver dynamic contrast-enhanced magnetic resonance (DCE-MR) imaging remains challenging because of intensity variations caused by contrast agents. Such variations lead to the failure of the traditional intensity-based registration method. To address this problem, we propose a correlation-weighted sparse representation framework to separate the contrast agent from original liver DCE-MR images. This framework allows the robust registration of motion components over time without intensity variances. Existing sparse coding techniques recover a 3D image containing only contrast agents (named contrast enhancement component) from a manually labeled dictionary, whose column has the same size with the original 3D volume (3D-t mode). The high dimension of the recovery target (3D volume) and the indistinguishability between the unenhanced and enhanced images make accurate coding difficult. In this paper, we predefine an ideal time-intensity curve containing only contrast agents (named contrast agent curve) and recover it from the transpose dictionary (t-3D mode), whose column has been updated into the original time-intensity curves. The low dimension of the target (1D curve) and the significant intergroup difference between contrast agent curves and non-contrast agent curves can estimate a series of pure contrast agent curves. A "correlation-weighted" constraint is introduced for the selection of a coding subset with more contrast agent curves, leading to an efficient and accurate sparse recovery process. Then, the contrast enhancement component can be estimated by the solved sparse coefficients' map and the ideal curve and subtracted from the original DCE-MRI. Finally, we register the de-enhanced images and apply the obtained deformation fields for the original DCE-MRI to achieve the goal of motion correction. We conduct the experiments on both simulated and real liver DCE-MRI data. Compared with other state-of-the-art DCE-MRI registration methods, the experimental results show that our method achieves a better registration performance with less computational efficiency.

Designing deep CNN models based on sparse coding for aerial imagery: a deep-features reduction approach

ABSTRACT Traditional methods focus on low-level handcrafted features representations and it is difficult to design a comprehensive classification algorithm for remote sensing scene classification problems. Recently, convolutional neural networks (CNNs) have obtained remarkable performance outcomes, setting several remote sensing benchmarks. Furthermore, direct applications of UAV remote sensing images that use deep convolutional networks are extremely challenging given high input data dimensionality with relatively small amounts of available labelled data. We, therefore, propose a CNN approach to scene classification that architecturally incorporates sparse coding (SC) technique for dimension reduction to minimize overfitting. Outcomes were compared with principal component analysis (PCA) and global average pooling (GAP) alternatives that use fully connected layer(s) in pre-trained CNN architecture(s) to minimize overfitting. SC was used to encode deep features extracted from the last convolutional layer of pre-trained CNN models by using different features maps in which deep features had been converted into low-dimensional SC features. These same sparse-coded features were concatenated by means of different pooling techniques to obtain global image features for scene classification. The proposed algorithm outperformed current state-of-the-art algorithms based on handcrafted features. When using our own UAV-based dataset and existing datasets, it was also exceptionally efficient computationally when learning data representations, producing a 93.64% accuracy rate..