Few-shot image classification (FSIC) aims to recognize novel categories from only a few labeled examples, making it inherently challenging under limited supervision. Existing approaches have attempted to alleviate this issue by incorporating explicit semantics like class names or knowledge graphs to guide learning. However, such methods often encounter semantic ambiguity due to their dependence on either overly simplistic semantic priors or resource-intensive external knowledge sources, which limits their potential. In this paper, we explore the frequency domain as an implicit and task-adaptive source of semantic information. We propose F2SST, a Frequency-to-Spatial Semantic Transfer framework that enhances feature learning by leveraging spectral signals as hidden semantics. Specifically, F2SST applies Fast Fourier Transform (FFT) to extract phase-invariant global frequency descriptors, followed by a lightweight Gated Spectral Attention (GSA) module that selectively emphasizes class-relevant frequency components. These enhanced spectral cues are then integrated into the spatial stream through a class-guided fusion mechanism, enabling more robust and semantically aligned representations. Extensive experiments on four standard benchmarks (miniImageNet, tieredImageNet, CIFAR-FS and FC100) demonstrate that F2SST consistently improves performance, validating the effectiveness of frequency-domain semantics in FSIC.

Reasoning Video Object Segmentation (ReasonVOS) is a challenging task that requires stable object segmentation across video sequences using implicit and complex textual inputs. Previous methods fine-tune Multimodal Large Language Models (MLLMs) to produce segmentation outputs, which demand substantial resources. Additionally, some existing methods are coupled in the processing of spatio-temporal information, which affects the temporal stability of the model to some extent. To address these issues, we propose Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory (SDAM). We aim to design a training-free reasoning video segmentation framework that outperforms existing methods requiring fine-tuning, using only pre-trained models. Meanwhile, we propose an Adaptive Object Memory module that selects and memorizes key objects based on motion cues in different video sequences. Finally, we propose Spatio-temporal Decoupling for stable temporal propagation. In the spatial domain, we achieve precise localization and segmentation of target objects, while in the temporal domain, we leverage key object temporal information to drive stable cross-frame propagation. Our method achieves excellent results on five benchmark datasets, including Ref-YouTubeVOS, Ref-DAVIS17, MeViS, ReasonVOS, and ReVOS.

Open-world few-shot classification is restricted by inadequate image-level content representation capabilities when the training and testing sets have significant differences in categories. Recently, many studies show the effectiveness of deep local descriptor-based methods, which attempt to select out dominating contents and discard noisy ones. However, aforementioned methods focus more on external relevance of support and query sets to filter features and ignore internal relevance among support sets, leading to unsatisfying classification performance. To relieve the issue, in this article, we propose the complementary learning Decoupling Category-Region-Aware Network (DCRNet) to simultaneously learn the correlation between internal members and then interact with the external sets. Specifically, we first propose an effective learnable Category Prototype-generated Feature Decoupling Module (CPFDM) to mine co-existing representations and generate comprehensive global class prototype. Then, to adaptively filter out discriminative local descriptors, we present a Category-Aware Selection Module (CASM) and introduce the Category-Aware Contrastive Loss (CACL) to highlight local information that is highly relative to the current category. In addition, the Region-Aware Contrastive Loss (RACL) is designed to encourage the model to concentrate on local regions, yielding powerful ability to distinguish foreground regions from between various categories. Finally, we leverage the filtered support descriptors to adaptively refine query descriptors through the descriptor selection strategy. Extensive experiments demonstrate that the proposed solution outperforms state-of-the-arts on five mainstream general and fine-grained few-shot classification datasets. We have released the training and testing code on https://github.com/jjfang007/DCRNet .

The recent end-to-end neural solvers have shown promise for small-scale routing problems but suffered from limited real-time scaling-up performance. This paper proposes GLOP (Global and Local Optimization Policies), a unified hierarchical framework that efficiently scales toward large-scale routing problems. GLOP hierarchically partitions large routing problems into Travelling Salesman Problems (TSPs) and TSPs into Shortest Hamiltonian Path Problems. For the first time, we hybridize non-autoregressive neural heuristics for coarse-grained problem partitions and autoregressive neural heuristics for fine-grained route constructions, leveraging the scalability of the former and the meticulousness of the latter. Experimental results show that GLOP achieves competitive and state-of-the-art real-time performance on large-scale routing problems, including TSP, ATSP, CVRP, and PCTSP. Our code is available at: https://github.com/henry-yeh/GLOP.

Image cartoonization has attracted significant interest in the field of image generation. However, most of the existing image cartoonization techniques require re-training models using images of cartoon style. In this paper, we present CartoonDiff, a novel training-free sampling approach which generates image cartoonization using diffusion transformer models. Specifically, we decompose the reverse process of diffusion models into the semantic generation phase and the detail generation phase. Furthermore, we implement the image cartoonization process by normalizing high-frequency signal of the noisy image in specific denoising steps. CartoonDiff doesn’t require any additional reference images, complex model designs, or the tedious adjustment of multiple parameters. Extensive experimental results show the powerful ability of our CartoonDiff. The project page is available at: https://cartoondiff.github.io/

Few-shot image classification aims to classify images from unseen novel classes with few samples. Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features. However, most existing methods solely rely on either employing all local descriptors or directly utilizing partial descriptors, potentially resulting in the loss of crucial information. Moreover, these methods primarily emphasize the selection of query descriptors while overlooking support descriptors. In this paper, we propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net), which exhibits the capacity for adaptive selection of task-aware support descriptors and query descriptors. Specifically, we compare the similarity of each local support descriptor with other local support descriptors to obtain the optimal support descriptor subset and then compare the query descriptors with the optimal support subset to obtain discriminative query descriptors. Extensive experiments demonstrate that our TALDS-Net outperforms state-of-the-art methods on both general and fine-grained datasets1.

Few-shot image classification is a challenging task aim to classific unseen images in scenarios with limited samples. Recent work demonstrate that local discriminative features have better representational capabilities than global features. In this paper, we propose a novel method to extract local discriminative features from images and calculate better class representations through contrastive learning. We divide the training paradigm into two stages, referred to as pre-training and meta-training. In the pre-training stage, we employ a global contrastive loss and introduce an improved Mutual Maximum Local Matching Contrastive Loss (MMCL) to obtain local discriminative features while disregarding irrelevant background features. During the meta-training stage, we introduce a new contrastive learning-based Adaptive Class Representation Computation Network (ACRC-Net) to enhance the generalization capability of class representations. It has the ability to adaptively compute class representations, specifically by comparing the similarity between features of the same and different classes within the same tasks to obtain the optimal subset of class representations. Based on the optimal subset of representations, we obtain the final class representation. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods on general datasets.

The potential of transformer in addressing few-shot learning problems remains largely untapped, primarily due to the current challenges in maintaining a robust inductive bias. This limitation contributes to the performance degradation observed in few-shot tasks. To alleviate this issue, we propose a two-stage few-shot learning framework based on the Vision Transformer, named Task-Adaptive Token Matching (TATM). Specifically, our approach utilizes advanced masked image modeling during pretraining to obtain discriminative representations of samples and capture long-range semantic correspondences. Following that, we empower the model with adaptive capabilities tailored to various tasks, employing a dual-loop meta-finetuning paradigm. Our key innovation lies in establishing finer-grained dependencies among image patches within the task, enabling the model to identify the most meaningful patch for the current task. This enhancement strengthens the transformer architecture’s locality and translation equivariance, introducing a degree of inductive bias that motivates the model’s resistance to overfitting. Furthermore, inspired by contrastive learning, we incorporate a penalty term into the few-shot classification loss function. This term is employed to balance the relationship between intra-class and inter-class variations. Our experimental evaluations on three mainstream few-shot benchmarks under 5-way 5-shot and 1-shot settings demonstrate that the TATM significantly improves the classification performance of few-shot tasks.

On behalf of the ICIS 2023 organizing committee, it is a great pleasure and honor to welcome you all come to the 23rd IEEE/ACIS International Conference on Computer and Information Science, to be held on June 23-24, 2023 in Wuxi, China. This year ICIS 20223 is in in cooperation with Jiangnan University, China

Few-shot learning for image classification task aims to classify images from several novel classes with limited number of samples. Recent studies have shown that the deep local descriptors have better representation ability than image-level features, and achieve great success. However, most of these methods often use all local descriptors or over-screening local descriptors for classification. The former contains some task-irrelevant descriptors, which may misguide the final classification result. The latter is likely to lose some key descriptors. In this paper, we propose a novel Task-Aware Discriminant local descriptors Network (TADNet) to address these issues, which can adaptively select the discriminative query descriptors and eliminate the task-irrelevant query descriptors among the entire task. Specifically, TADNet assigns a value to each query descriptor by comparing its similarity to all support classes to represent its discriminant power for classification. Then the discriminative query descriptors can be preserved via a task-aware attention map. Extensive experiments on both fine-grained and generalized datasets demonstrate that the proposed TADNet outperforms the existing state-of-the-art methods.

Few-shot learning aims to learn generalized knowledge from limited data, which is a challenging study. Metric-based few-shot learning is the most widely studied direction, and most metric-based methods focus on how to learn a more robust feature embedding space or distance metric for classification. Few-shot learning is trained with a large number of tasks. Most existing methods do not realize that the role of the same sample in different learning tasks may be different, which will affect the effectiveness of classification. This paper proposes a task-adaptive feature adjustment method to obtain new features with task context information and more discrimination to solve this problem. We also introduce the Sphere manifold into few-shot learning, use the manifold metric instead of the Euclidean metric, and deduce the gradient optimization on the manifold. We propose a novel few-shot learning method with an excellent performance by combining these two innovations. We conduct several experiments on the few-shot learning benchmark datasets to demonstrate the advancement of our methods. The experimental results have significantly improved over the baseline and are highly competitive with the mainstream and effective methods.

Few-shot classification (FSC) aims to recognize novel classes with few labeled samples in each class. Currently, meta-learning methods have achieved great success in few-shot classification tasks. However, most methods assume that base classes and novel classes share a single domain, and their performance can be greatly reduced when comes to domain-shift problem. To further improve the generalization of the existing FSC models, we propose a novel Self-Challenging Module including the Self-Challenging Mask and random noise. Self-Challenging Mask exploits the relationship between mid-level feature maps and high-level feature vectors to challenge (greatly weaken) the dominant mid-level local descriptors which are extracted in focus. Therefore, the model is forced to discover the residual information that correlates with the classification task from the remaining mid-level local descriptors. This method appears to expand the feature distribution for generalizing on unseen domains. We combine our method with three existing metric-based FSC model and conduct a large number of classification experiments in five datasets under the setting of cross-domain few-shot classification. The result shows that our Self-Challenging Module can significantly improve the classification accuracy in both seen and unseen domains.

Meta-learning aims to learn some common knowledge quickly from the limited labeled examples. Semi-supervised meta-learning is developed to improve the learning performance of the learner using limited labeled data and available unlabeled data. This paper proposes a new semi-supervised meta-learning method called the class-wise attention reinforcement (CWAR) method from the distinction of class representation and the credibility of pseudo-labeling. Firstly, we propose a class-wise attention (CWA) module to generate the class-wise attention weight vectors and apply them to prototype, query set, and unlabeled auxiliary set, reinforcing the attention on critical features in the task. Then, we use the random data augmentation method to assign pseudo labels to unlabeled data. Moreover, to mitigate the effects of misclassification and noise-influenced samples on the prototype, generating weight as the coefficient to calculate the new prototype. Experimental results on two popular benchmarks demonstrate the proposed method’s effectiveness and have highly competitive performance compared with the state-of-the-art.

Meta-learning is proven to be powerful for helping models make quick adaptations to new tasks. However, the lack of data severely constrains the further improvement. As data augmentation has been an effective and commonly used approach to reach state-of-art performance in image classification tasks, different strategies for applying data augmentation to meta-learning have emerged. One common combination of data augmentation and meta-learning is performing different transformations on images(e.g. horizontal flip, color jitter, and random crop) before feeding them to the feature extractor. Another way is using generative models, such as GAN, to expand the available dataset and alleviate the negative effects of lack of data. These methods either have limited boosts or have difficulties to converge during training and require significant extra computation. In this paper, we propose a novel method using a modified Variational Auto Encoder(VAE) to generate dummy samples from the support set. Our data augmentation method is performed in the feature space to reduce computation steps. Combined with prototypical networks we call our method as Prototype Augmentation with Dummy Samples(PADS). Experiments are carried out both in standard few-shot image classification and cross-domain scenarios and we achieved significant improvement with comparison to the baseline.

Few-shot learning is dedicated to dealing with the dependence of deep learning on a large amount of data. It learns some new concepts through a large number of training tasks instead of a large amount of data, which enables it learn new tasks quickly without a large amount of training data. Compared with other meta-learning methods, the effect of metric-based meta-learning methods is more advantageous. Despite the success of metric-based meta-learning approaches, the adaptability of metric methods to data distribution is still insufficient, which leads to classification results more dependent on the accuracy of encoder networks and are susceptible to noisy features. In this paper, we realize the filtering of noisy features and the correction of data distribution by adaptive learning of metric weights and data distribution biases, and propose corresponding loss functions to evaluate and update our adaptive module and encoding network. Experimental results on standard few-shot learning datasets demonstrate that our proposed method achieves good improvement.

In recent years, few-shot classification algorithms have been developing. But many few-shot classification algorithms are facing their bottlenecks. After our study and research of the Prototypical Network, we found that the prototype calculation method and loss function are relatively simple, which can be improved better. We present our few-shot classification algorithm in this paper, which is inspired by Prototypical Network and center loss function. Based on the Prototypical Network, we propose our Adaptive Weights Model(AWM) to give each sample a better weight parameter, so that we can get a more reasonable prototype. Based on this model, bad samples(Contain a lot of noise) will get a smaller weight, while good samples(Contain very little noise) will get a larger weight. Based on the center loss function, we propose our Adaptive Sample’s Distribution Model(ASDM), which enables us to optimize the distribution of samples. Then, we did a lot of experiments based on our model. The results show that the our model is effective. Few-shot learning is becoming more and more important in machine learning. However, most few-shot learning algorithms only rely on deep neural networks to process samples. Here, we offer a different idea to give more reasonable weights to the samples.

Abstract Due to the varying appearance in the upper clavicle bone region, sharp corner at the costophrenic angle, the presence of strong edges at the rib cage and clavicle and the lack of a consistent anatomical shape among different individuals, accurate segmentation of lung on chest radiographs remains challenging. In this work, we propose a novel segmentation method for lung segmentation, containing two subnetworks, where few manually delineated points are used as the approximate initialization. The first one is a preprocessing subnetwork based on a deep learning model (i.e. Deep Belief Network and K-Nearest Neighbor). The second one is a refinement subnetwork, designed to make the preprocessed result to be optimized by combining an improved principal curve method and a machine learning method. To prove the performance of the proposed method, several public datasets were evaluated with Dice Similarity Coefficient (DSC), overlap score (Ω), Sensitivity (Sen), Positive Predictive Value (PPV), global Error (E) and execution time (t). Compared with state-of-the-art methods, our method reaches superior segmentation performance.

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Particularly, employing meta-learning for few-shot classification has achieved remarkable advances. However, the uncertainty problem triggered by the noisy data or modeling assumptions hinders the performance of existing approaches to be further improved. To tackle the above issue, this paper proposes a novel meta-learning approach called Symplectic Group Bayesian Manifold Network (SGBMN) for a more accurate classification prediction. Specifically, we adopt symplectic group bayesian matrix to represent each input data point, such that the uncertainty problem caused by complex data could be alleviated. Then, a manifold space is constructed by combing the above symplectic group bayesian matrices, in which the optimization can be performed by natural gradient descent. We conduct extensive experiments on two real-world image datasets and the results demonstrate that our proposed method outperforms several baseline approaches.

In solving learning problems with limited training data, few-shot learning is proposed to remember some common knowledge by leveraging a large number of similar few-shot tasks and learning how to adapt a base-learner to a new task for which only a few labeled samples are available. Among different few-shot learning algorithms, metric-based methods, which focus on how to acquire a robust feature embedding space or distance metric for classification, are most studied and believed to be effective for classification tasks. Despite the success of the metric-based methods, the distribution of training data and test data in the same few shot classification task is inconsistent with a distribution bias between them, which affects the quality of feature embeddings. In addition, the way of directly comparing the original features as a whole is deficient. It doesn't emphasize the features with high correlation between samples and thus can't distinguish the differences adequately. This manuscript proposes a novel metric-based few-shot algorithm called Task-adaptive Relation Dependent Network. The method reduces the distribution bias by shifting the dataset and adopting a more detailed comparison of features to capture their intrinsic correspondence, improving the measurements of the similarity between the support set and the query set samples. An experiment is conducted and the results demonstrate that the proposed method has a significant improvement over the baseline on the standard few-shot image classification benchmark datasets.

Meta-learning classification is about training a classifier by remembering some common knowledge from limited labeled examples in a support set. It has attracted more and more attention in machine learning community. Despite the success, existing Meta-learning algorithms usually ignore the relationship between the samples of the support set and the samples of the query set in a task after feature extraction and thus fail to obtain the most discriminative features, which leads to an unreliable class prototype and a low distinguishability of feature representations. In this paper, we propose a novel metric-based meta-learning algorithm called Prototype Enhancement Network (PEN) to tackle the above problems. The proposed algorithm uses: (1) a Task Context-Related (TCR) Module to obtain a more discriminative and context-related feature representation of samples within a task; and (2) a Prototype Reset (PR) module to expands the support set with partially unlabeled query set samples to mitigate the low-data problem and obtain a more representative class prototype. The cooperation of the TCR module and the PR module effectively enhance the reliability and the accuracy of the class prototype. Experiments are conducted on two classification benchmarks (mini-ImageNet and tiered-ImageN et) and the results confirm the effectiveness of PEN compared with other state-of-the-art methods.

Few-shot classification aims to recognize unlabeled samples from unseen classes given only a few labeled samples. Current approaches of few-shot learning usually employ a metric-learning framework to learn a feature similarity comparison between a query (test) example and the few support (training) examples. However, these approaches all extract features from samples independently without looking at the entire task as a whole, and so fail to provide an enough discrimination to features. Moreover, the existing approaches lack the ability to select the most relevant features for the task at hand. In this work, we propose a novel algorithm calledTask-AwareAttentionNetwork(TAAN) to address the above problems in few-shot classification. By inserting aTask-RelevantChannelAttentionModuleinto metric-based few-shot learners, TAAN generates channel attentions for each sample by aggregating the context of the entire support set and identifies the most relevant features for similarity comparison. The experiment demonstrates that TAAN is competitive in overall performance comparing to the recent state-of-the-art systems and improves the performance considerably over baseline systems on both mini-ImageNet and tiered - ImageNet benchmarks.

For the problems of data sparseness and cold start of goods in the existing recommendation algorithm, in this paper, we propose a new method based on the hidden Bayesian method to predict user preferences. Our approach is to use the variational Bayesian non-negative matrix factorization on observable rating matrices (users- items), which can predict the filling of the scoring matrix and cluster the users. On this basis, the user's hidden information and pre-rating are obtained, and the pre-rating is corrected in combination with the item attribute information by improved naive Bayes classifier. Experimental results show that 1) this method does not require additional clustering algorithms, which saves execution time. 2) Compared with the classical matrix factorization and similarity algorithm, our method solves the cold start problem of new items and the greatly improved the accuracy of recommendation.

Multi-view data provide more comprehensive information than single views by providing different feature sets of the same object. Learning its data structure through spectral clustering has always been the mainstream of research. However, due to the limitation of its core graph theory, traditional spectral graph-based multi-view clustering algorithms are inapplicable for analyzing large-scale data sets. In this paper, we propose MultiSpectralNet (MvSN), a deep learning approach to spectral multi-view clustering, provides mapping multi-view data points to their fusion eigenvectors and can obtain a more accurate data structure by correcting the misleading information in the single views to a certain extent by feedback in the network training process. In addition, our model can cluster large multi-view data sets and provide cluster prediction for out-of-sample extension. We test ACC and normalized mutual information (NMI) of our method in clustering several artificial and real-world data sets, and the experimental results show that our method outperforms conventional compared state-of-the-art works.

Due to the incorporation of dimensionality reduction, spectral clustering (SC) based methods have a unique advantage in dealing with high-dimensional data. However, data is mainly characterized by its distribution on multiple low-dimensional manifolds, which is ignored by some SC-based methods. We put forward a new spectral multi-manifold embedded clustering (SMEC) method in this paper, which incorporates the local geometric information of data into the traditional SC. Thus, the designed similarity matrix in SMEC is able to capture both the local and global discriminating information, which results in improved clustering. Experimental results on seven benchmark datasets demonstrate our proposed method's promising performance.

As a manifold learning algorithm, unsupervised large graph embedding (ULGE) has been proposed to deal with large-scale dataset for clustering. This paper improves ULGE and proposes a graph embedding-based ensemble learning (GEEL) algorithm. We take the dimensionality reduction algorithm in ULGE and the K-means clustering algorithm as an individual learner in our ensemble learning. For each individual learner, the K-means clustering method is first used to generate anchors. Then, the low-dimensional embedding of the sample data is obtained. Finally, the K-means clustering method is used again and performed on the low-dimensional data, which results in a clustering. The diversity of ensemble learning lies on the unstable of K-means. To combine multiple clusterings, we first match these clusterings with a reference clustering using the bestMap method, where the reference clustering is randomly chosen from multiple ones. A majority voting rule is adopted to these matched clusterings to generate the final clustering. A large number of experiments show the efficiency and effectiveness of the proposed method.

Multi-label image annotation is one of the most important open problems in machine learning and computer vision. In this paper, we propose a novel model for image annotation. Unlike existing works that usually use conventional visual features to annotate images, this paper adopts features based on convolutional neural network (CNN), which have shown potential to achieve outstanding performance. In particular, we use CNN to extract image features with higher semantic meaning and apply them to the image annotation method - Tag Propagation (TagProp). Experimental results on four challenging datasets indicate that our model makes a marked improvement as compared to the current state-of-the-art.

Single sample face recognition has always been a hot but difficult issue in face recognition. The existing methods solve this issue from selecting robust features or generating virtual samples. By considering selecting robust features and generating virtual samples simultaneously, this paper proposes a multi-scale support vector transformation (MSSVT) based method to generate multi-scale virtual samples for single image recognition. Experimental results on three face data sets verify that the proposed algorithm retains most information and has the best performance compared with other related algorithm.

The research and analysis on multi-source data is one of important tasks in information science. Compared with traditional single-source data learning algorithms, multi-source data learning ones can describe objects more real and complete. Meanwhile, the learning process of multi-source data is more in line with the cognitive mechanism of human brain. So far, the research on multi-source data learning algorithms includes three classes, multi-source data transfer learning, multi-source data collaborative learning and multi-source multi-view learning. The traditional multi-source multi-view learning algorithms lack the ability of handling with the data missing issue, which means that these algorithms require the multi-source data to be complete. This paper proposes a multi-source clustering algorithm. Based on the spectral properties of Laplace operator, we first obtain the complete representation of multi-source data. Then, we utilize the multi-view spectral embedding (MVSE) to construct the fusion model. Experimental results show that our proposed method can improve the ability of clustering efficiently in the case of data missing.

This paper proposes a novel Nonnegative and Adaptive Multi-view Clustering (NAMC) method. NAMC integrates the nonnegative matrix factorization (NMF), adaptive neighborhood learning and consensus adaptive similarity matrix fusion. More specifically, NAMC performs the nonnegative weight learning over the original data and the parts-based representations of NMF for more accurate measure and representation. For nonnegative adaptive feature extraction, our model first utilizes NMF to obtain the local parts-based representation of the original high-dimensional data. To keep the local structure of parts-based representations, we minimize the adaptive neighborhood reconstruction error. Then the optimal consensus similarity matrix can be iteratively obtained according to the nonnegative adaptive similarity matrix of each view. What's more, the proposed NAMC is totally self-weighted. Once the target graph is obtained in our model, it can be partitioned into specific clusters directly. Extensive simulations show that NAMC can achieve good performance on several public databases for multi-view clustering, compared with other related methods.

In this paper, we propose an analysis mechanism-based structured analysis discriminative dictionary learning analysis discriminative dictionary learning, framework. The ADDL seamlessly integrates ADDL, analysis representation, and analysis classifier training into a unified model. The applied analysis mechanism can make sure that the learned dictionaries, representations, and linear classifiers over different classes are independent and discriminating as much as possible. The dictionary is obtained by minimizing a reconstruction error and an analytical incoherence promoting term that encourages the subdictionaries associated with different classes to be independent. To obtain the representation coefficients, ADDL imposes a sparse -norm constraint on the coding coefficients instead of using or norm, since the - or -norm constraint applied in most existing DL criteria makes the training phase time consuming. The code-extraction projection that bridges data with the sparse codes by extracting special features from the given samples is calculated via minimizing a sparse code approximation term. Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers. Thus, the classification approach of our model is very efficient, because it can avoid the extra time-consuming sparse reconstruction process with trained dictionary for each new test data as most existing DL algorithms. Simulations on real image databases demonstrate that our ADDL model can obtain superior performance over other state of the arts.

We propose a robust inductive semi-supervised label prediction model over the embedded representation, termed adaptive embedded label propagation with weight learning (AELP-WL), for classification. AELP-WL offers several properties. First, our method seamlessly integrates the robust adaptive embedded label propagation with adaptive weight learning into a unified framework. By minimizing the reconstruction errors over embedded features and embedded soft labels jointly, our AELP-WL can explicitly ensure the learned weights to be joint optimal for representation and classification, which differs from most existing LP models that perform weight learning separately by an independent step before label prediction. Second, existing models usually precalculate the weights over the original samples that may contain unfavorable features and noise decreasing performance. To this end, our model adds a constraint that decomposes original data into a sparse component encoding embedded noise-removed sparse representations of samples and a sparse error part fitting noise, and then performs the adaptive weight learning over the embedded sparse representations. Third, our AELP-WL computes the projected soft labels by trading-off the manifold smoothness and label fitness errors over the adaptive weights and the embedded representations for enhancing the label estimation power. By including a regressive label approximation error for simultaneous minimization to correlate sample features with the embedded soft labels, the out-of-sample issue is naturally solved. By minimizing the reconstruction errors over features and embedded soft labels, classification error and label approximation error jointly, state-of-the-art results are delivered.

Both neighbourhood preserving embedding (NPE) and sparsity preserving projection (SPP) are unsupervised learning methods, where NPE can preserve the local neighbourhood information of a given dataset and SPP can preserve the sparsely reconstructive relationship of the dataset. However, it is not satisfactory when applying the two methods to classification tasks. First, a modified SPP is presented here. Then this study proposes a supervised sparse neighbourhood preserving embedded algorithm (SSNPE) based on NPE, the modified SPP and the label information of a given task. SSNPE inherits the merits of NPE and SPP, which can preserve not only the local neighbourhood information but also the sparsely reconstructive relationship. The connection between SSNPE and both NPE and SPP is discussed. Experimental results on the datasets of UCI, ORL and MNIST indicate that the proposed method is effective.

This study proposes a supervised orthogonal discriminant projection (SODP) based on double adjacency graphs (DAGs). SODP based on DAG (SODP‐DAG) aims to minimise the local within‐class scatter and simultaneously maximise both the local between‐class scatter and the non‐local scatter, where the local between‐class scatter and the local within‐class scatter are constructed by applying the DAG structure. By doing so, SODP‐DAG can keep the local within‐class structure for original data and find the optimal discriminant directions effectively. Moreover, four schemes are designed for constructing weight matrices in SODP‐DAG. To validate the performance of SODP‐DAG, the authors compared it with orthogonal discriminant projection, SODP and others on several publicly available datasets. Experimental results show the feasibility and effectiveness of SODP‐DAG.

This paper investigates the salient machine faults representation-based classification issue by dictionary learning. A novel structured latent label consistent dictionary learning (LLC-DL) model is proposed for joint discriminative salient representation and classification. Our LLC-DL deals with the tasks by solving one objective function that aims to minimize the structured reconstruction error, structured discriminative sparse-code error and classification error simultaneously. Also, LLC-DL decomposes given signals into a sparse reconstruction part over structured latent weighted discriminative dictionary, a salient feature extraction part and an error part fitting noise. Specifically, the dictionary is learnt atom by atom, where each dictionary atom is learnt with a latent vector that reduces the disturbance between interclass atoms. The structured coding coefficients are calculated via minimizing the reconstruction error and discriminative sparse code error simultaneously. The salient representations are learnt by embedding signals onto a projection and a robust linear classifier is then trained over the learned salient features directly so that features can be ensured to be optimal for classification, where robust l2,1-norm imposed on the classifier can make the prediction results more accurate. By including a salient feature extraction term, the classification approach of LLC-DL is very efficient, since there is no need to involve an extra time-consuming sparse reconstruction process with the well-trained dictionary for each test signal. Extensive simulations versify the effectiveness of our algorithm.

We propose two nuclear- and L2,1-norm regularized 2D neighborhood preserving projection (2DNPP) methods for extracting representative 2D image features. 2DNPP extracts neighborhood preserving features by minimizing a Frobenius norm-based reconstruction error that is very sensitive noise and outliers in given data. To make the distance metric more reliable and robust, and encode the neighborhood reconstruction error more accurately, we minimize the nuclear- and L2,1-norm-based reconstruction error, respectively and measure it over each image. Technically, we propose two enhanced variants of 2DNPP, nuclear-norm-based 2DNPP and sparse reconstruction-based 2DNPP. Besides, to optimize the projection for more promising feature extraction, we also add the nuclear- and sparse L2,1-norm constraints on it accordingly, where L2,1-norm ensures the projection to be sparse in rows so that discriminative features are learnt in the latent subspace and the nuclear-norm ensures the low-rank property of features by projecting data into their respective subspaces. By fully considering the neighborhood preserving power, using more reliable and robust distance metric, and imposing the low-rank or sparse constraints on projections at the same time, our methods can outperform related state-of-the-arts in a variety of simulation settings.

We propose a nuclear-norm regularized two-dimensional neighborhood preserving projection (2DNPP) for extracting representative 2D image features. Note that 2DNPP extracts neighborhood preserving features through minimizing the reconstruction error, but the Frobenius norm based metric is sensitive to noise and outliers. To make the distance metric more reliable and model the neighborhood reconstruction error more accurately, we impose the nuclear-norm on the neighborhood reconstruction error and measure it over each image. Technically, we propose a new variant of 2DNPP termed nuclear-norm based 2DNPP (N-2DNPP). Besides, to make delivered projection promising for feature extraction, we also include the nuclear-norm constraint on projection accordingly, where the low-rank projection can embed data into their respective subspaces. Our method can outperform related state-of-the-arts in a variety of simulation settings.

L1-norm maximization based Discriminant Locality Preserving Projection (DLPP-L1) is shown to be effective and robust to the outliers in given data, but DLPP-L1 is based on the vector space, so it has to convert those 2D matrices into high-dimensional 1D vectorized representations when handing images. But such transformation usually destroys the topology structures of images pixels, which can decrease performance. We therefore propose to extend DLPP-L1 to the 2D matrix space. A two-dimensional DLPP-L1, termed 2D-DLPP-L1, is technically proposed for image feature extraction. Compared with DLPP-L1 for representation, our proposed 2D-DLPP-L1 can effectively preserve the topology structures among image pixels in addition to inheriting the robustness property against noise and outliers. Extensive simulations on real-world image datasets show that our 2D-DLPP-L1 can deliver enhanced performance over other state-of-the-arts for recognition.

We propose a Joint nuclear norm based nonlinear Manifold Learning through linear embedding with Classification, called JMLC. By including a feature approximation error into the existing nonlinear manifold learning framework to correlate manifold features with embedded features by a linear projection, the learnt projection can handle the outside points efficiently by embedding. Besides, to encode the neighborhood reconstruction error in manifold learning part, we apply a more reliable nuclear norm based distance metric, since nuclear norm is proved to be more reliable than both L1-norm and Frobenius norm. To make learnt nonlinear features be optimal for classification so that the accuracy can be enhanced, we also minimize a robust L2,1-norm based regressive classification error over the embedded manifold features, which ensures the classification process to be robust to noise and outliers in data. Based on performing joint manifold learning and classification alternately, our JMLC can obtain a low-dimensional embedding, a linear projection and a multi-class classifier simultaneously. Extensive results demonstrate the validity of our proposed algorithm for feature extraction and robust classification, compared with other related models.

We propose a new discriminative dictionary learning framework termed Latent Label Consistent K-SVD (LLC-KSVD) for representing and classifying machine faults. Our LLC-KSVD handles the task by minimizing the reconstruction, discriminative sparse-code and classification errors at the same time. To enhance the representation and classification powers, LLC-KSVD aim to decompose given data into a sparse reconstruction part, a salient feature part and an error part. The salient features are learnt by embedding data onto a projection and a classifier is then trained over extracted salient features so that features are ensured to be optimal for classification. Thus, the classification approach of our LLC-KSVD is very efficient, since there is no need to involve a time-consuming sparse reconstruction process with well-trained dictionary for each test signal as existing models. Besides, to make the classifier be robust to noise and outliers, we regularize the l2,¿-norm on classifier so that the predictions are more accurate. Simulations on several machine fault datasets demonstrate the state-of-the-art performance by our LLC-KSVD.

In this paper, we propose a semisupervised label consistent dictionary learning (SSDL) framework for machine fault classification. SSDL is a semisupervised extension of recent fully supervised label consistent dictionary learning approach, since the number of labeled machine data is usually limited in practice. To enable the supervised dictionary learning model to use both labeled and commonly readily available unlabeled data for enhancing performance, we propose to incorporate the merits of label prediction and present a joint label consistent dictionary learning and adaptive label prediction technique. In this setting, we first employ the existing label prediction model to estimate the labels of unlabeled training signals in a transductive fashion for enriching supervised prior. Then, we use predicted labeled data for label consistent dictionary learning. After that, we apply the discriminant sparse codes as the adaptive reconstruction weights for label prediction to update the estimated labels of unlabeled training data and the discriminative sparse codes matrix for label consistent dictionary learning so that classification performance can be enhanced. Thus, an informative dictionary, a sparse-code matrix, and an optimal multiclass classifier can be alternately obtained from one objective function. Besides, the tricky process of choosing optimal kernel width and neighborhood size can also be effectively voided in our scheme due to the adaptive weights. Extensive simulations on several machine fault datasets show that our SSDL method can deliver enhanced performance over other state-of-the-arts for machine fault classification.

Recovering low-rank and sparse subspaces jointly for enhanced robust representation and classification is discussed. Technically, we first propose a transductive low-rank and sparse principal feature coding (LSPFC) formulation that decomposes given data into a component part that encodes low-rank sparse principal features and a noise-fitting error part. To well handle the outside data, we then present an inductive LSPFC (I-LSPFC). I-LSPFC incorporates embedded low-rank and sparse principal features by a projection into one problem for direct minimization, so that the projection can effectively map both inside and outside data into the underlying subspaces to learn more powerful and informative features for representation. To ensure that the learned features by I-LSPFC are optimal for classification, we further combine the classification error with the feature coding error to form a unified model, discriminative LSPFC (D-LSPFC), to boost performance. The model of D-LSPFC seamlessly integrates feature coding and discriminative classification, so the representation and classification powers can be enhanced. The proposed approaches are more general, and several recent existing low-rank or sparse coding algorithms can be embedded into our problems as special cases. Visual and numerical results demonstrate the effectiveness of our methods for representation and classification.

In this paper, we propose a L1-Norm driven Semi-Supervised Local Discriminant Projection (S2LDP-L1) for robust dimensionality reduction and image representation. For feature learning, our S2LDP-L1 approach aims at compacting local within-class divergence and separating local betweenclass divergence at the same time in addition to possessing the locality preserving power over all training data. To enable the presented S2LDP-L1 method to be robust against noise in data for feature reduction and representation, the L1-norm that is proven to be robust to noise and outliers is regularized on the constructed scatter matrices for measuring pairwise similarities/ dissimilarities between samples. Thus, the presentation power can be effectively enhanced to improve the subsequent classification task. The derived ratio based model is finally solved by an iterative approach to deliver a discriminating and neighborhood preserving orthogonal projection for extracting features from both training and test samples by embedding data onto it. For classification, an existing label propagation model is used to identify the categories of test data. Extensive results on handwriting digit datasets verified the validity of our S2LDP-L1, compared with other state-of-the-arts.

In this paper, we mainly present a Semi-Supervised Label Consistent KSVD (S2KSVD) algorithm for representing and classifying machine faults. The formulation of our S2KSVD is an improvement to the recent label consistent K-SVD (LC-KSVD), because LC-KSVD is a fully supervised approach, and needs to use supervised class information of all training data to compute a reconstructive & discriminative dictionary. But labeled signals are often expensive to obtain, while in contrast unlabeled signals can be easily captured with low expense from the real world. Thus, the application of LC-KSVD may be constrained in reality. To address this problem, we present S2KSVD through involving a computationally efficient label propagation (LP) process as a preprocessing step. The core idea is to employ the LP process to estimate the labels of unlabeled signals so that supervised prior knowledge that can significantly enhance classification can be increased. Simulation results on several machine fault datasets demonstrate that our algorithm delivers promising performance for machine fault classification.

This paper proposes an enhanced semi-supervised classification approach termed Nonnegative Sparse Neighborhood Propagation (SparseNP) that is an improvement to the existing neighborhood propagation due to the fact that the outputted soft labels of points cannot be ensured to be sufficiently sparse, discriminative, robust to noise and be probabilistic values. Note that the sparse property and strong discriminating ability of predicted labels is important, since ideally the soft label of each sample should have only one or few positive elements (that is, less unfavorable mixed signs are included) deciding its class assignment. To reduce the negative effects of unfavorable mixed signs on the learning performance, we regularize the l2,1-norm on the soft labels during optimization for enhancing the prediction results. The non-negativity and sum-to-one constraints are also included to ensure the outputted labels are probabilistic values. The proposed framework is solved in an alternative manner for delivering a more reliable solution so that the accuracy can be improved. Simulations show that satisfactory results can be obtained by the proposed SparseNP compared with other related approaches.

Supervised locally linear embedding (SLLE) has been proposed for classification tasks. SLLE can take full use of the label information and select neighbours only in the same class. However, SLLE uses the least squares (LSs) method for solving a set of linear equations to obtain linear representation coefficients, which relates to the inverse of a matrix. If the matrix is singular, the solution to the set of linear equations does not exist. Additionally, if the size of neighbourhood is not appropriate, some further neighbours along the manifold would be selected. To remedy those, this study deals with SLLE based on orthogonal matching pursuit (SLLE‐OMP) by introducing OMP into SLLE. In SLLE‐OMP, LS is replaced by OMP and OMP can reselect new neighbours from old ones. Experimental results on some real‐world datasets show that SLLE‐OMP can achieve better classification performance compared with SLLE.

Traditional label propagation (LP) is shown to be effective for transductive classification. To enable the standard LP to handle outside images, two inductive methods by label reconstruction or by direct embedding have been presented, of which the latter scheme is relatively more efficient, especially for testing. But almost all inductive LP models use 1D vectors of images as inputs, which may destroy the topology structure of image pixels and usually suffer from high complexity due to the high dimension of 1D vectors in reality. To preserve the topology among pixels and address the scalability issue for the embedding based scheme, we propose a simple yet efficient Bilinear Embedding Label Propagation (BELP) by including a bilinear regularization term in terms of tensor representation to correlate the image labels with their bilinear features. BELP performs label prediction over the 2D matrices rather than 1D vectors, since images are essentially matrices. Finally, labels of new images can be easily obtained by embedding them onto a spanned bilinear subspace solved from a joint framework. Simulations verified the efficiency of our approach.

An enhanced label propagation technique termed transformed neighborhood propagation (TNP) is proposed for semi-supervised learning. In the TNP setting, the processes of constructing weighted similarity graph and propagating label information of the labeled data to unlabeled points are conducted in the transformed feature space. TNP is mainly motivated by a fact that the optimal feature representation Y with possible unfavorable features and noises in the original data X removed by feature learning are more appropriate and accurate for measuring pair wise similarities of samples. To achieve the representation Y, The recent marginal semi-supervised sub-manifold projections is applied, so enhanced inter-class separation and enhanced intra-class compactness are delivered at the same time. The similarity graph is finally constructed based on Y. We also propose to calculate semi-supervised reconstruction weights for the weight assignment. As a result, the label estimation power can be enhanced by benefiting from the refined weighted similarity graph over Y instead of X, through propagating the labels of points in the transformed space for prediction. Visualization and image classification verified the effectiveness of our TNP, compared with other related label propagation algorithms.

For low-rank recovery and error correction, Low-Rank Representation (LRR) row-reconstructs given data matrix X by seeking a low-rank representation, while Inductive Robust Principal Component Analysis (IRPCA) aims to calculate a low-rank projection to column-reconstruct X. But either column or row information of Xis lost by LRR and IRPCA. In addition, the matrix X itself is chosen as the dictionary by LRR, but (grossly) corrupted entries may greatly depress its performance. To solve these issues, we propose a simultaneous low-rank representation and dictionary learning framework termed Tensor LRR (TLRR) for robust bilinear recovery. TLRR reconstructs given matrix X along both row and column directions by computing a pair of low-rank matrices alternately from a nuclear norm minimization problem for constructing a low-rank tensor subspace. As a result, TLRR in the optimizations can be regarded as enhanced IRPCA with noises removed by low-rank representation, and can also be considered as enhanced LRR with a clean informative dictionary using a low-rank projection. The comparison with other criteria shows that TLRR exhibits certain advantages, for instance strong generalization power and robustness enhancement to the missing values. Simulations verified the validity of TLRR for recovery.