Emerging from the pairwise attention in conventional Transformers, there is a growing interest in sparse attention mechanisms that align more closely with localized, contextual learning in the biological brain. Existing studies such as the Coordination method employ iterative cross-attention mechanisms with a bottleneck to enable the sparse association of inputs. However, these methods are parameter inefficient and fail in more complex relational reasoning tasks. To this end, we propose Associative Transformer (AiT) to enhance the association among sparsely attended input tokens, improving parameter efficiency and performance in various vision tasks such as classification and relational reasoning. AiT leverages a learnable explicit memory comprising specialized priors that guide bottleneck attentions to facilitate the extraction of diverse localized tokens. Moreover, AiT employs an associative memory-based token reconstruction using a Hopfield energy function. The extensive empirical experiments demonstrate that AiT requires significantly fewer parameters and attention layers outperforming a broad range of sparse Transformer models. Additionally, AiT outperforms the SOTA sparse Transformer models including the Coordination method on the Sort-of-CLEVR dataset.
Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual unit (e.g,, pixel or patch) in a uniform manner. In this paper, we challenge this dense paradigm and present a new method, coined SparseFormer, to imitate human's sparse visual recognition in an end-to-end manner. SparseFormer learns to represent images using a highly limited number of tokens (down to 49) in the latent space with sparse feature sampling procedure instead of processing dense units in the original pixel space. Therefore, SparseFormer circumvents most of dense operations on the image space and has much lower computational costs. Experiments on the ImageNet classification benchmark dataset show that SparseFormer achieves performance on par with canonical or well-established models while offering better accuracy-throughput tradeoff. Moreover, the design of our network can be easily extended to the video classification with promising performance at lower computational costs. We hope that our work can provide an alternative way for visual modeling and inspire further research on sparse neural architectures. The code will be publicly available at https://github.com/showlab/sparseformer
We describe a minimalistic and interpretable method for unsupervised learning, without resorting to data augmentation, hyperparameter tuning, or other engineering designs, that achieves performance close to the SOTA SSL methods. Our approach leverages the sparse manifold transform, which unifies sparse coding, manifold learning, and slow feature analysis. With a one-layer deterministic sparse manifold transform, one can achieve 99.3% KNN top-1 accuracy on MNIST, 81.1% KNN top-1 accuracy on CIFAR-10 and 53.2% on CIFAR-100. With a simple gray-scale augmentation, the model gets 83.2% KNN top-1 accuracy on CIFAR-10 and 57% on CIFAR-100. These results significantly close the gap between simplistic "white-box" methods and the SOTA methods. Additionally, we provide visualization to explain how an unsupervised representation transform is formed. The proposed method is closely connected to latent-embedding self-supervised methods and can be treated as the simplest form of VICReg. Though there remains a small performance gap between our simple constructive model and SOTA methods, the evidence points to this as a promising direction for achieving a principled and white-box approach to unsupervised learning.
This paper proposes a low-cost and highly accurate ECG-monitoring system intended for personalized early arrhythmia detection for wearable mobile sensors. Earlier supervised approaches for personalized ECG monitoring require both abnormal and normal heartbeats for the training of the dedicated classifier. However, in a real-world scenario where the personalized algorithm is embedded in a wearable device, such training data is not available for healthy people with no cardiac disorder history. In this study, (i) we propose a null space analysis on the healthy signal space obtained via sparse dictionary learning, and investigate how a simple null space projection or alternatively regularized least squares-based classification methods can reduce the computational complexity, without sacrificing the detection accuracy, when compared to sparse representation-based classification. (ii) Then we introduce a sparse representation-based domain adaptation technique in order to project other existing users' abnormal and normal signals onto the new user's signal space, enabling us to train the dedicated classifier without having any abnormal heartbeat of the new user. Therefore, zero-shot learning can be achieved without the need for synthetic abnormal heartbeat generation. An extensive set of experiments performed on the benchmark MIT-BIH ECG dataset shows that when this domain adaptation-based training data generator is used with a simple 1-D CNN classifier, the method outperforms the prior work by a significant margin. (iii) Then, by combining (i) and (ii), we propose an ensemble classifier that further improves the performance. This approach for zero-shot arrhythmia detection achieves an average accuracy level of 98.2% and an F1-Score of 92.8%. Finally, a personalized energy-efficient ECG monitoring scheme is proposed using the above-mentioned innovations.
Sparse representation-based classification (SRC) has attracted much attention by casting the recognition problem as simple linear regression problem. SRC methods, however, still is limited to enough labeled samples per category, insufficient use of unlabeled samples, and instability of representation. For tackling these problems, an unlabeled data driven inverse projection pseudo-full-space representation-based classification model is proposed with low-rank sparse constraints. The proposed model aims to mine the hidden semantic information and intrinsic structure information of all available data, which is suitable for few labeled samples and proportion imbalance between labeled samples and unlabeled samples problems in frontal face recognition. The mixed Gauss-Seidel and Jacobian ADMM algorithm is introduced to solve the model. The convergence, representation capability and stability of the model are analyzed. Experiments on three public datasets show that the proposed LR-S-PFSRC model achieves stable results, especially for proportion imbalance of samples.
Identifying seizure activities in non-stationary electroencephalography (EEG) is a challenging task, since it is time-consuming, burdensome, and dependent on expensive human resources and subject to error and bias. A computerized seizure identification scheme can eradicate the above problems, assist clinicians and benefit epilepsy research. So far, several attempts were made to develop automatic systems to help neurophysiologists accurately identify epileptic seizures. In this research, a fully automated system is presented to automatically detect the various states of the epileptic seizure. The proposed method is based on sparse representation-based classification (SRC) theory and the proposed dictionary learning using electroencephalogram (EEG) signals. Furthermore, the proposed method does not require additional preprocessing and extraction of features which is common in the existing methods. The proposed method reached the sensitivity, specificity and accuracy of 100% in 8 out of 9 scenarios. It is also robust to the measurement noise of level as much as 0 dB. Compared to state-of-the-art algorithms and other common methods, the proposed method outperformed them in terms of sensitivity, specificity and accuracy. Moreover, it includes the most comprehensive scenarios for epileptic seizure detection, including different combinations of 2 to 5 class scenarios. The proposed automatic identification of epileptic seizures method can reduce the burden on medical professionals in analyzing large data through visual inspection as well as in deprived societies suffering from a shortage of functional magnetic resonance imaging (fMRI) equipment and specialized physician.
Sparse approximation is the problem to find the sparsest linear combination for a signal from a redundant dictionary, which is widely applied in signal processing and compressed sensing. In this project, I manage to implement the Orthogonal Matching Pursuit (OMP) algorithm and Sparse Representation-based Classification (SRC) algorithm, then use them to finish the task of masked image classification with majority voting. Here the experiment was token on the AR data-set, and the result shows the superiority of OMP algorithm combined with SRC algorithm over masked face image classification with an accuracy of 98.4%.
Representation based classification methods have become a hot research topic during the past few years, and the two most prominent approaches are sparse representation based classification (SRC) and collaborative representation based classification (CRC). CRC reveals that it is the collaborative representation rather than the sparsity that makes SRC successful. Nevertheless, the dense representation of CRC may not be discriminative which will degrade its performance for classification tasks. To alleviate this problem to some extent, we propose a new method called sparse and collaborative-competitive representation based classification (SCCRC) for image classification. Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively. Then the fused coefficient is derived by multiplying the coefficients of SRC and CCRC. Finally, the test sample is designated to the class that has the minimum residual. Experimental results on several benchmark databases demonstrate the efficacy of our proposed SCCRC. The source code of SCCRC is accessible at https://github.com/li-zi-qi/SCCRC.
We consider the problem of robust face recognition in which both the training and test samples might be corrupted because of disguise and occlusion. Performance of conventional subspace learning methods and recently proposed sparse representation based classification (SRC) might be degraded when corrupted training samples are provided. In addition, sparsity based approaches are time-consuming due to the sparsity constraint. To alleviate the aforementioned problems to some extent, in this paper, we propose a discriminative low-rank representation method for collaborative representation-based (DLRR-CR) robust face recognition. DLRR-CR not only obtains a clean dictionary, it further forces the sub-dictionaries for distinct classes to be as independent as possible by introducing a structural incoherence regularization term. Simultaneously, a low-rank projection matrix can be learned to remove the possible corruptions in the testing samples. Collaborative representation based classification (CRC) method is exploited in our proposed method which has closed-form solution. Experimental results obtained on public face databases verify the effectiveness and robustness of our method.
This work follows the approach of multi-label classification for non-intrusive load monitoring (NILM). We modify the popular sparse representation based classification (SRC) approach (developed for single label classification) to solve multi-label classification problems. Results on benchmark REDD and Pecan Street dataset shows significant improvement over state-of-the-art techniques with small volume of training data.
Sparse-representation-based classification (SRC) has been widely studied and developed for various practical signal classification applications. However, the performance of a SRC-based method is degraded when both the training and test data are corrupted. To counteract this problem, we propose an approach that learns Representation with Block-Diagonal Structure (RBDS) for robust image recognition. To be more specific, we first introduce a regularization term that captures the block-diagonal structure of the target representation matrix of the training data. The resulting problem is then solved by an optimizer. Last, based on the learned representation, a simple yet effective linear classifier is used for the classification task. The experimental results obtained on several benchmarking datasets demonstrate the efficacy of the proposed RBDS method.
Sparse representation-based classification (SRC) has been shown to achieve a high level of accuracy in face recognition (FR). However, matching faces captured in unconstrained video against a gallery with a single reference facial still per individual typically yields low accuracy. For improved robustness to intra-class variations, SRC techniques for FR have recently been extended to incorporate variational information from an external generic set into an auxiliary dictionary. Despite their success in handling linear variations, non-linear variations (e.g., pose and expressions) between probe and reference facial images cannot be accurately reconstructed with a linear combination of images in the gallery and auxiliary dictionaries because they do not share the same type of variations. In order to account for non-linear variations due to pose, a paired sparse representation model is introduced allowing for joint use of variational information and synthetic face images. The proposed model, called synthetic plus variational model, reconstructs a probe image by jointly using (1) a variational dictionary and (2) a gallery dictionary augmented with a set of synthetic images generated over a wide diversity of pose angles. The augmented gallery dictionary is then encouraged to pair the same sparsity pattern with the variational dictionary for similar pose angles by solving a newly formulated simultaneous sparsity-based optimization problem. Experimental results obtained on Chokepoint and COX-S2V datasets, using different face representations, indicate that the proposed approach can outperform state-of-the-art SRC-based methods for still-to-video FR with a single sample per person.
We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully-connected layer. The role of the autoencoder network is to learn robust deep features for classification. On the other hand, the fully-connected layer, which is placed in between the encoder and the decoder networks, is responsible for finding the sparse representation. The estimated sparse codes are then used for classification. Various experiments on three different datasets show that the proposed network leads to sparse representations that give better classification results than state-of-the-art SRC methods. The source code is available at: github.com/mahdiabavisani/DSRC.
In this letter, we propose a novel computationally efficient coupled dictionary learning method that enforces pairwise correlation between the atoms of dictionaries learned to represent the underlying feature spaces of two different representations of the same signals, e.g., representations in different modalities or representations of the same signals measured with different qualities. The jointly learned correlated feature spaces represented by coupled dictionaries are used in sparse representation based classification, recognition and reconstruction tasks. The presented experimental results show that the proposed coupled dictionary learning method has a significantly lower computational cost. Moreover, the visual presentation of jointly learned dictionaries shows that the pairwise correlations between the corresponding atoms are ensured.
Sparse representation based classification (SRC) methods have achieved remarkable results. SRC, however, still suffer from requiring enough training samples, insufficient use of test samples and instability of representation. In this paper, a stable inverse projection representation based classification (IPRC) is presented to tackle these problems by effectively using test samples. An IPR is firstly proposed and its feasibility and stability are analyzed. A classification criterion named category contribution rate is constructed to match the IPR and complete classification. Moreover, a statistical measure is introduced to quantify the stability of representation-based classification methods. Based on the IPRC technique, a robust tumor recognition framework is presented by interpreting microarray gene expression data, where a two-stage hybrid gene selection method is introduced to select informative genes. Finally, the functional analysis of candidate's pathogenicity-related genes is given. Extensive experiments on six public tumor microarray gene expression datasets demonstrate the proposed technique is competitive with state-of-the-art methods.
We consider the decomposition of a signal over an overcomplete set of vectors. Minimization of the $\ell^1$-norm of the coefficient vector can often retrieve the sparsest solution (so-called "$\ell^1/\ell^0$-equivalence"), a generally NP-hard task, and this fact has powered the field of compressed sensing. Wright et al.'s sparse representation-based classification (SRC) applies this relationship to machine learning, wherein the signal to be decomposed represents the test sample and columns of the dictionary are training samples. We investigate the relationships between $\ell^1$-minimization, sparsity, and classification accuracy in SRC. After proving that the tractable, deterministic approach to verifying $\ell^1/\ell^0$-equivalence fundamentally conflicts with the high coherence between same-class training samples, we demonstrate that $\ell^1$-minimization can still recover the sparsest solution when the classes are well-separated. Further, using a nonlinear transform so that sparse recovery conditions may be satisfied, we demonstrate that approximate (not strict) equivalence is key to the success of SRC.
Recently the sparse representation based classification (SRC) has been proposed for robust face recognition (FR). In SRC, the testing image is coded as a sparse linear combination of the training samples, and the representation fidelity is measured by the l2-norm or l1-norm of the coding residual. Such a sparse coding model assumes that the coding residual follows Gaussian or Laplacian distribution, which may not be effective enough to describe the coding residual in practical FR systems. Meanwhile, the sparsity constraint on the coding coefficients makes SRC's computational cost very high. In this paper, we propose a new face coding model, namely regularized robust coding (RRC), which could robustly regress a given signal with regularized regression coefficients. By assuming that the coding residual and the coding coefficient are respectively independent and identically distributed, the RRC seeks for a maximum a posterior solution of the coding problem. An iteratively reweighted regularized robust coding (IR3C) algorithm is proposed to solve the RRC model efficiently. Extensive experiments on representative face databases demonstrate that the RRC is much more effective and efficient than state-of-the-art sparse representation based methods in dealing with face occlusion, corruption, lighting and expression changes, etc.
Using low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e.g. bomb or mine, has been successfully demonstrated recently. Despite promising recent progress, a significant open challenge is to distinguish obscured targets from other (natural and manmade) clutter sources in the scene. The problem becomes exacerbated in the presence of noisy responses from rough ground surfaces. In this paper, we present three novel sparsity-driven techniques, which not only exploit the subtle features of raw captured data but also take advantage of the polarization diversity and the aspect angle dependence information from multi-channel SAR data. First, the traditional sparse representation-based classification (SRC) is generalized to exploit shared information of classes and various sparsity structures of tensor coefficients for multi-channel data. Corresponding tensor dictionary learning models are consequently proposed to enhance classification accuracy. Lastly, a new tensor sparsity model is proposed to model responses from multiple consecutive looks of objects, which is a unique characteristic of the dataset we consider. Extensive experimental results on a high-fidelity electromagnetic simulated dataset and radar data collected from the U.S. Army Research Laboratory side-looking SAR demonstrate the advantages of proposed tensor sparsity models.
Single-sample face recognition is one of the most challenging problems in face recognition. We propose a novel algorithm to address this problem based on a sparse representation based classification (SRC) framework. The new algorithm is robust to image misalignment and pixel corruption, and is able to reduce required gallery images to one sample per class. To compensate for the missing illumination information traditionally provided by multiple gallery images, a sparse illumination learning and transfer (SILT) technique is introduced. The illumination in SILT is learned by fitting illumination examples of auxiliary face images from one or more additional subjects with a sparsely-used illumination dictionary. By enforcing a sparse representation of the query image in the illumination dictionary, the SILT can effectively recover and transfer the illumination and pose information from the alignment stage to the recognition stage. Our extensive experiments have demonstrated that the new algorithms significantly outperform the state of the art in the single-sample regime and with less restrictions. In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class. Furthermore, the face recognition accuracy exceeds those of the SRC and Extended SRC algorithms using hand labeled alignment initialization.
Sparse representation based classification (SRC) has been proved to be a simple, effective and robust solution to face recognition. As it gets popular, doubts on the necessity of enforcing sparsity starts coming up, and primary experimental results showed that simply changing the $l_1$-norm based regularization to the computationally much more efficient $l_2$-norm based non-sparse version would lead to a similar or even better performance. However, that's not always the case. Given a new classification task, it's still unclear which regularization strategy (i.e., making the coefficients sparse or non-sparse) is a better choice without trying both for comparison. In this paper, we present as far as we know the first study on solving this issue, based on plenty of diverse classification experiments. We propose a scoring function for pre-selecting the regularization strategy using only the dataset size, the feature dimensionality and a discrimination score derived from a given feature representation. Moreover, we show that when dictionary learning is taking into account, non-sparse representation has a more significant superiority to sparse representation. This work is expected to enrich our understanding of sparse/non-sparse collaborative representation for classification and motivate further research activities.