At present, spectral clustering is an important branch of unsupervised learning, and its application in deep learning has been widely concerned. However, for high-dimensional sparse datasets, the complexity of network scale leads to parameter explosion, and static Gaussian kernel often has wrong preset data structure. To overcome these challenges, we propose a novel deep clustering model, Deep Clustering Based on Sparse Kolmogorov-Arnold Network (KAN) and Spectral Constraint. It contains a deep sparse clustering framework, in which sparse KAN and the orthogonal layer are designed to enhance the sparsity of the activation function matrix, reduce the number of parameters and improve the stability of model convergence. Additionally, we add an adaptive optimized affinity matrix based on spectral constraint, which overcomes the limitations of static Gaussian kernels, and improves the performance and stability of spectral constraint. Experimental results on both synthetic and real datasets demonstrate that our model outperforms existing methods in clustering performance, computational efficiency, and stability.

In the past era of explosive data growth, how to deal with large-scale, unlabeled remote sensing images (RSIs) has become a concern. Due to the lack of data labels, unsupervised methods are usually used to deal with them. As one of the best unsupervised algorithms, spectral clustering (SC) is a very effective data processing and analysis technology. However, the scalability of SC affects its development in the era of big data. Deep network technology has developed rapidly in the past, and it is often used to solve the problem of out-of-sample expansion (OOSE) that traditional machine learning cannot solve. However, because RSI is usually high-dimensional data, it is easy to cause dimension explosion in deep networks. The main motivation of this work is to solve the above problems. We have designed a new algorithm called deep SC with projected adaptive feature selection (DSCFS), which benefits from deep learning theory and feature projection technology. We use a neural network to map RSI data and then further process the data through regularization embedding. At the same time, adaptive feature projection is applied to extract the main features of RSI, and the loss feedback network is calculated through these two steps. A large number of experiments show that the performance of our proposed method is better than other mainstream methods.

Gait recognition has become a mainstream technology for identification, as it can recognize the identity of subjects from a distance without any cooperation. However, when subjects wear coats (CL) or backpacks (BG), their gait silhouette will be occluded, which will lose some gait information and bring great difficulties to the identification. Another important challenge in gait recognition is that the gait silhouette of the same subject captured by different camera angles varies greatly, which will cause the same subject to be misidentified as different individuals under different camera angles. In this article, we try to overcome these problems from three aspects: data augmentation, feature extraction, and feature refinement. Correspondingly, we propose gait sequence mixing (GSM), multigranularity feature extraction (MFE), and feature distance alignment (FDA). GSM is a method that belongs to data enhancement, which uses the gait sequences in NM to assist in learning the gait sequences in BG or CL, thus reducing the influence of lost gait information in abnormal gait sequences (BG or CL). MFE explores and fuses different granularity features of gait sequences from different scales, and it can learn as much useful information as possible from incomplete gait silhouettes. FDA refines the extracted gait features with the help of the distribution of gait features in real world and makes them more discriminative, thus reducing the influence of various camera angles. Extensive experiments demonstrate that our method has better results than some state-of-the-art methods on CASIA-B and mini-OUMVLP. We also embed the GSM module and FDA module into some state-of-the-art methods, and the recognition accuracy of these methods is greatly improved.

Spectral clustering (SC) is a well-performed and prevalent technique for data processing and analysis, which has attracted significant attention in the field of clustering. While the scalability and generalization ability of this method make it prohibitive for the large-scale dataset and the out-of-sample-extension problem. In this work, we propose a new efficient deep clustering architecture based on SC, named deep SC (DSC) with constrained Laplacian rank (DSCCLR). DSCCLR develops a self-adaptive affinity matrix with a clustering-friendly structure by constraining the Laplacian rank, which greatly mines the intrinsic relationships. Meanwhile, by introducing a simple fully connected network with an orthogonality constraint on the last layer, DSCCLR learns discriminative representations in a short training time. The proposed method has the following salient properties: 1) it overcomes limited generalization ability and scalability of the existing DSC methods; 2) it explores the intrinsic relationship between samples in the affinity matrix, which maintains the latent manifold of data as much as possible; and 3) it alleviates the complexity of eigendecomposition via a simple but effective fully connected network. The extensive empirical results demonstrate the superiorities of DSCCLR over other 17 clustering methods.

The past decade has witnessed the rapid development of deep learning techniques, especially for large-scale and complex data sets. However, it is still a noteworthy problem in dealing with unsupervised hyperspectral image segmentation since inefficiency and misleading result from the absence of supervised information. Generally, spectral clustering is one of the most powerful clustering algorithms, as it often outperforms other methods for image segmentation. Unfortunately, the poor scalability and generalization severely limit the use of spectral clustering, especially for large-scale and high-dimensional hyperspectral images processing. The major motivation of this work is to solve this problem, and we designed a novel algorithm, termed Deep Spectral Clustering with Regularized Linear Embedding (DSCRLE), to benefit from both spectral graph theory and deep learning techniques. The brief procedure is first to construct a fully connected neural network to extract latent feature representations, and then normalize the feature representations by the spectral orthonormal constraint. Lastly, by introducing low-dimensional embedding, we refined the final outputs of all given unlabeled hyperspectral pixels. Extensive experiments have demonstrated that the competitiveness of the proposed method, and it outperforms state-of-art clustering approaches in the task of hyperspectral image segmentation.

Spectral clustering is a well-known clustering algorithm for unsupervised learning, and its improved algorithms have been successfully adapted for many real-world applications. However, traditional spectral clustering algorithms are still facing many challenges to the task of unsupervised learning for large-scale datasets because of the complexity and cost of affinity matrix construction and the eigen-decomposition of the Laplacian matrix. From this perspective, we are looking forward to finding a more efficient and effective way by adaptive neighbor assignments for affinity matrix construction to address the above limitation of spectral clustering. It tries to learn an affinity matrix from the view of global data distribution. Meanwhile, we propose a deep learning framework with fully connected layers to learn a mapping function for the purpose of replacing the traditional eigen-decomposition of the Laplacian matrix. Extensive experimental results have illustrated the competitiveness of the proposed algorithm. It is significantly superior to the existing clustering algorithms in the experiments of both toy datasets and real-world datasets.

Gait recognition provides a more convenient way for human identification, as it can identify person with less cooperation and intrusion compared to other biometric features. Current gait recognition frameworks utilize a template to extract temporal feature or regard the whole person as a unit, and they obtain limited temporal information and fine-grained features. To overcome this problem, we propose a network consisting of two parts: Temporal Feature Fusion (TFF) and Fine-grained Feature Extraction (FFE). First, we extract the most representative temporal information from raw gait sequences by TFF. Next, we use the idea of partial features on fused temporal features to extract more fine-grained spatial block features. It is worth mentioning that the proposed algorithm provides an effective feature extraction framework for complex gait recognition, as it focuses on the temporal fusion for representative information, and the extraction of the fine-grained spatial features. Extensive experiments illustrated that we have an outstanding performance on CASIA-B and mini-OUMVLP compared to other state-of-the-art methods including GaitSet and GaitNet. In particularly, the average rank-1 accuracy of all probe views on normal walking condition (NM) achieve 95.7%.

As a new biometric feature, gait brings new possibilities for personal recognition. At present, gait recognition methods mainly extract appearance features, but seldom use temporal information, such as the method based on gait energy images (GEI) to fuse gait sequence into one image. In order to mine the motion patterns contained in gait sequences, this paper proposes a model that can gradually fuse temporal features while extracting spatial features to achieve the spatiotemporal feature extraction: 1) the model mines temporal information by passing partial channels of feature maps and fusing features of adjacent frames; 2) the model adapts the part-based method to split feature map into several parts, which can refine the spatial features. Extensive experiments on the challenging datasets CASIA-B demonstrate the superiority and effectiveness of our proposed model.

Gait information has gradually attracted people's attention duing to its uniqueness. Methods based on deep metric learning are successfully utlized in gait recognition tasks. However, most of the previous studies use losses which only consider a small number of samples in the mini-batch, such as Triplet loss and Quadruplet Loss, which is not conducive to the convergence of the model. Therefore, in this paper, a novel loss named Center-ranked is proposed to integrate all positive and negative samples information. We also propose a simple model for gait recognition tasks to verify the validity of the loss. Extensive experiments on two challenging datasets CASIA-B and OU-MVLP demonstrate the superiority and effectiveness of our proposed Center-ranked loss and model.