Partial label learning (PLL) aims to learn from the data where each instance is associated with a candidate label set, with only one being valid. Most existing approaches are designed to eliminate noisy labels and use the remaining reliable ones for model training, following a label-centric learning paradigm. In this paper, we propose a new PLL method called Semantic-Aware Feature Enhancement (SAFE), which tackles the problem through a novel feature-centric learning paradigm. SAFE presumes that the candidate labels are correct while the observed features are partial, and thus seeks to recover the underlying missing features. In this manner, a desired predictive model is constructed by integrating the observed and recovered features, which are responsible for predicting the true label and the remaining candidate labels, respectively. To ensure the quality of recovered features, SAFE jointly explores the intrinsic topological structures via dynamic graphs in both feature and label spaces as guidance for semantic-aware feature enhancement. Extensive experimental results on some popular datasets demonstrate the effectiveness and superiority of the proposed method over state-of-the-art PLL approaches.

Label Distribution Learning (LDL) is an effective machine learning paradigm for addressing label ambiguity, where each sample is annotated with a distribution that conveys rich semantic information. However, during the actual annotation process of label distributions, annotators often exhibit divergent labeling preferences for the same sample. Most existing LDL methods overlook this heterogeneity, assuming that the observed label distribution originates from a single labeling pattern. Such an assumption limits their capacity to manage inter-annotator disagreement and constrains the generalization of the resulting models. To address this issue, we propose, for the first time, a Dirichlet process mixture model (DPMM)-based framework for LDL. This framework leverages nonparametric Bayesian methods to adaptively uncover diverse latent labeling patterns from the data and to accurately model annotator heterogeneity. Specifically, the ground-truth label distribution of each sample is modeled as a weighted mixture of multiple latent components, where a feature-conditioned gating mechanism adaptively controls the contribution of each component. Experimental results demonstrate that the proposed model consistently achieves competitive performance on several widely-used benchmark datasets.

Label polysemy, where an instance can be associated with multiple labels, is common in real-world tasks. LDL (label distribution learning) is an effective learning paradigm for handling label polysemy, where each instance is associated with a label distribution. Although numerous LDL algorithms have been proposed and achieved satisfactory performance on most existing datasets, they are typically trained directly on the collected label distributions which often lack quality guarantees in real-world tasks due to annotator subjectivity and algorithm assumptions. Consequently, direct learning from such uncertain label distributions can lead to unpredictable generalization performance. To address this problem, we propose an adaptive-grained label distribution learning framework whose main idea is to extract relatively reliable supervision information from unreliable label distributions, and thus the label distribution learning task can be decomposed into three subtasks: coarsening label distributions, learning coarse-grained labels and refining coarse-grained labels. In this framework, we design an adaptive label coarsening algorithm to extract an optimal coarsen-grained labels and a label refining function to enhance the coarse-grained label into the final label distributions. Finally, we conduct extensive experiments on real-world datasets to demonstrate the advantages of our proposal.

The motivation of this paper originates from rethinking an essential characteristic of crowd counting: individuals (heads of humans) in the crowd counting task typically occupy a very small portion of the image. This characteristic has never been the focus of existing works: they typically use the same backbone as other visual tasks and pursue a large receptive field. This drives us to propose a new model design principle of crowd counting: emphasizing local modeling capability of the model. We follow the principle and design a crowd counting model named Local Information Matters Model (LIMM). The main innovation lies in two strategies: a window partitioning design that applies grid windows to the model input, and a window-wise contrastive learning design to enhance the model’s ability to distinguish between local density levels. Moreover, a global attention module is applied to the end of the model to handle the occasionally occurring large-sized individuals. Extensive experiments on multiple public datasets illustrate that the proposed model shows a significant improvement in local modeling capability (8.7% in MAE on the JHU-Crowd++ high-density subset for example), without compromising its ability to count large-sized ones, which achieves state-of-the-art performance. Code is available at: https://github.com/tianhangpan/LIMM.

Currently, most crowd counting methods have outstanding performance under normal weather conditions. However, our experimental validation reveals two key obstacles limiting the accuracy improvement of crowd counting models: 1) the domain gap between the adverse weather and the normal weather images; 2) the weather class imbalance in the training set. To address the problems, we propose a two-stage crowd counting method named Multi-queue Contrastive Learning (MQCL). Specifically, in the first stage, our target is to equip the backbone network with weather-awareness capabilities. In this process, a contrastive learning method named multi-queue MoCo designed by us is employed to enable representation learning under weather class imbalance. After the first stage is completed, the backbone model is capable of extracting weather-related representations. On this basis, we proceed to the second stage, in which we propose to refine the representations under the guidance of contrastive learning, enabling the conversion of the weather-aware representations to the normal weather domain. Through such representation and conversion, the model achieves robust counting performance under both normal and adverse weather conditions. Extensive experimental results show that, compared to the baseline, MQCL reduces the counting error under adverse weather conditions by 22%, while introducing only about 13% increase in computational burden, which achieves state-of-the-art performance.

Label distribution learning (LDL) is a powerful learning paradigm that emulates label polysemy by assigning label distributions over the label space. However, existing LDL evaluation metrics struggle to capture meaningful performance differences due to their insensitivity to subtle distributional changes, and existing LDL learning objectives often exhibit biases by disproportionately emphasizing a small subset of samples with extreme predictions. As a result, the LDL metrics lose their discriminability, and the LDL objectives are also at risk of overfitting. In this paper, we propose DeltaLDL, a percentage of predictions that are approximately correct within the context of LDL, as a solution to the above problems. DeltaLDL can serve as a novel evaluation metric, which is parameter-free and reflects more on real performance improvements. DeltaLDL can also serve as a novel learning objective, which is differentiable and encourages most samples to be predicted as approximately correct, thereby mitigating overfitting. Our theoretical analysis and empirical results demonstrate the effectiveness of the proposed solution.

Label distribution learning (LDL) is a novel machine learning paradigm that can handle label ambiguity. This paper focuses on the interpretability issue of label distribution learning. Existing local interpretability models are mainly designed for single-label learning problems and are difficult to directly interpret label distribution learning models. In response to this situation, we propose an improved local interpretable model-agnostic explanations algorithm that can effectively interpret any black-box model in label distribution learning. To address the label dependency problem, we introduce the feature attribution distribution matrix and derive the solution formula for explanations under the label distribution form. Meanwhile, to enhance the transparency and trustworthiness of the explanation algorithm, we provide an analytical solution and derive the boundary conditions for explanation convergence and stability. In addition, we design a feature selection scoring function and a fidelity metric for the explanation task of label distribution learning. A series of numerical experiments and human experiments were conducted to validate the performance of the proposed algorithm in practical applications. The experimental results demonstrate that the proposed algorithm achieves high fidelity, consistency, and trustworthiness in explaining LDL models.

Label distribution learning (LDL) is a novel learning paradigm that emulates label polysemy by assigning label distributions over the label space. However, recent LDL work seems to exhibit a notable contradiction: 1) existing LDL methods employ auxiliary tasks to enhance performance, which narrows their focus to specific applications, thereby lacking generalizability; 2) conversely, LDL methods without auxiliary tasks rely on losses tailored solely to the primary task, lacking beneficial data to guide the learning process. In this paper, we propose S-LDL, a novel and minimalist solution that generates subtask label distributions, i.e., a form of extra supervised information, to reconcile the above contradiction. S-LDL encompasses two key aspects: 1) an algorithm capable of generating subtasks without any prior/expert knowledge; and 2) a plug-andplay framework seamlessly compatible with existing LDL methods, and even adaptable to derivative tasks of LDL. Our analysis and experiments demonstrate that S-LDL is effective and efficient. To the best of our knowledge, this paper represents the first endeavor to address LDL via subtasks.

Label Distribution Learning (LDL) has emerged as a powerful framework for estimating complete conditional label distributions, providing crucial reliability for risk-sensitive decision-making tasks. While existing LDL algorithms exhibit competent performance under the conventional LDL performance evaluation methods, two key limitations remain: (1) current algorithms systematically underperform on the samples with low-entropy label distributions, which can be particularly valuable for decision making, and (2) the conventional performance evaluation methods are inherently biased due to the numerical imbalance of samples. In this paper, through empirical and theoretical analyses, we find that excessive cohesion between anchor vectors contributes significantly to the observed entropy bias phenomenon in LDL algorithms. Accordingly, we propose an inter-anchor angular regularization term that mitigates cohesion among anchor vectors by penalizing over-small angles. Besides, to alleviate the numerical imbalance of high-entropy samples in test set, we propose an entropy-calibrated aggregation strategy that obtains the overall model performance by evaluating performance on the low-entropy and high-entropy subsets of the overall test set separately. Finally, we conduct extensive experiments on various real-world datasets to demonstrate the effectiveness of our proposal.

Label distribution in recent years has been applied in a diverse array of complex decision-making tasks. To address the availability of label distributions, label enhancement has been established as an effective learning paradigm that aims to automatically infer label distributions from readily available multi-label data, e.g., logical labels. Recently, numerous works have demonstrated that the label ranking is significantly beneficial to label enhancement. However, these works still exhibit deficiencies in representing the probabilistic relationships between label distribution and label rankings, or fail to accommodate scenarios where multiple labels are equally important for a given instance. Therefore, we propose PROM, a pairwise ranking model with orderliness and monotonicity, to explain the probabilistic relationship between label distributions and label rankings. Specifically, we propose the monotonicity and orderliness assumptions for the probabilities of different ranking relationships and derive the mass functions for PROM, which are theoretically ensured to preserve the monotonicity and orderliness. Further, we propose a generative label enhancement algorithm based on PROM, which directly learns a label distribution predictor from the readily available multi-label data. Finally, extensive experiments demonstrate the efficacy of our proposed model.

Label distribution learning (LDL) suffers from the dilemma of insufficient target data in real-world applications, while domain adaptation (DA) seems to be able to provide a solution. However, most existing methods of DA, assuming that the instances can correspond to the explicit class information, are devoted only to classification but not to LDL. We argue that indiscriminately applying such DA methods might cause performance degradation in LDL tasks. In this paper, we propose LDL-DA, a novel algorithm dedicated to supervised domain adaptation for label distribution learning, which jointly learns a shared encoding representation from two aspects: 1) contrastive alignment of scarce supervised target data, and 2) minimizing the distance between prototypes of the same label combination. Experiments show that LDL-DA outperforms existing DA methods adapted to LDL, and provides early positive results in DA for LDL. To the best of our knowledge, this paper is the first research on DA for LDL.

Multi-view clustering (MVC) has attracted increasing attention with the emergence of various data collected from multiple sources. In real-world dynamic environment, instances are continually gathered, and the number of views expands as new data sources become available. Learning for such simultaneous increment of instances and views, particularly in unsupervised scenarios, is crucial yet underexplored. In this paper, we address this problem by proposing a novel MVC method with Incremental Instances and Views, MVC-IIV for short. MVC-IIV contains two stages, an initial stage and an incremental stage. In the initial stage, a basic latent multi-view subspace clustering model is constructed to handle existing data, which can be viewed as traditional static MVC. In the incremental stage, the previously trained model is reused to guide learning for newly arriving instances with new views, transferring historical knowledge while avoiding redundant computations. In specific, we design and reuse two modules, i.e., multi-view embedding module for low-dimensional representation learning, and consensus centroids module for cluster probability learning. By adding consistency regularization on the two modules, the knowledge acquired from previous data is used, which not only enhances the exploration within current data batch, but also extracts the between-batch data correlations. The proposed model can be efficiently solved with linear space and time complexity. Extensive experiments demonstrate the effectiveness and efficiency of our method compared with the state-of-the-art approaches.

Hashing methods have sparked a great revolution in cross-modal retrieval due to the low cost of storage and computation. Benefiting from the sufficient semantic information of labeled data, supervised hashing methods have shown better performance compared with unsupervised ones. Nevertheless, it is expensive and labor intensive to annotate the training samples, which restricts the feasibility of supervised methods in real applications. To deal with this limitation, a novel semisupervised hashing method, i.e., three-stage semisupervised hashing (TS3H) is proposed in this article, where both labeled and unlabeled data are seamlessly handled. Different from other semisupervised approaches that learn the pseudolabels, hash codes, and hash functions simultaneously, the new approach is decomposed into three stages as the name implies, in which all of the stages are conducted individually to make the optimization cost-effective and precise. Specifically, the classifiers of different modalities are learned via the provided supervised information to predict the labels of unlabeled data at first. Then, hash code learning is achieved with a simple but efficient scheme by unifying the provided and the newly predicted labels. To capture the discriminative information and preserve the semantic similarities, we leverage pairwise relations to supervise both classifier learning and hash code learning. Finally, the modality-specific hash functions are obtained by transforming the training samples to the generated hash codes. The new approach is compared with the state-of-the-art shallow and deep cross-modal hashing (DCMH) methods on several widely used benchmark databases, and the experiment results verify its efficiency and superiority.

Label distribution learning (LDL) is an effective learning paradigm for handling label ambiguity. When applying LDL, it typically requires datasets annotated with label distributions. However, obtaining supervised data for LDL is a challenging task. Due to the randomness of label annotation, the annotator can produce inaccurate annotation results for the instance, affecting the accuracy and generalization ability of the LDL model. To address this problem, we propose a generative approach to calibrate the inaccurate annotation for LDL using variational inference techniques. Specifically, we assume that instances with similar features share latent similar label distributions. The feature vectors and label distributions are generated by Gaussian mixture and Dirichlet mixture, respectively. The relationship between them is established through a shared categorical variable, which effectively utilizes the label distribution of instances with similar features, and achieves a more accurate label distribution through the generative approach. Furthermore, we use a confusion matrix to model the factors that contribute to the inaccuracy during the annotation process, which captures the relationship between label distributions and inaccurate label distributions. Finally, the label distribution is used to calibrate the available information in the noisy dataset to obtain the ground-truth label distribution.

Due to its effectiveness and efficiency, anchor based multi-view clustering (MVC) has recently attracted much attention. Most existing approaches try to adaptively learn anchors to construct an anchor graph for clustering. However, they generally focus on improving the diversity among anchors by using orthogonal constraint and ignore the underlying semantic relations, which may make the anchors not representative and discriminative enough. To address this problem, we propose an adaptive Cluster-wise Anchor learning based MVC method, CAMVC for short. We first make an anchor cluster assumption that supposes the prior cluster structure of target anchors by pre-defining a consensus cluster indicator matrix. Based on the prior knowledge, an explicit cluster structure of latent anchors is enforced by learning diverse cluster centroids, which can explore both inter-cluster diversity and intra-cluster consistency of anchors, and improve the subspace representation discrimination. Extensive results demonstrate the effectiveness and superiority of our proposed method compared with some state-of-the-art MVC approaches.

Polyp segmentation plays a crucial role in the prevention of colon cancer. However, the diverse shapes of polyps and their similarity to normal areas in terms of color and texture make polyp segmentation a challenging task. Currently, most polyp segmentation methods solely focus on spatial domain features, ignoring the valuable features in the frequency domain. Consequently, many polyp segmentation algorithms struggle with the camouflage of polyps. To tackle this issue, we propose the Frequency Aware and Graph Fusion Network (FAGF-Net). Specifically, it begins with a Frequency-based Global Extraction Module (FGEM), which provides an initial estimation of the polyp regions to guide subsequent modules. Next, we design a Frequency-based Feature Attention Module (FFAM) that leverages amplitude and phase information to amplify appearance differences and enhance semantic representations. Moreover, we present a Graph-based Fusion Module (GFM), which infers the geometric characteristic of polyps through aggregating and interacting with enhanced features. Extensive experiments show that our method outperforms state-of-the-art methods with better quantitative and qualitative evaluations.

Image deraining aims to recover clean images from degradation caused by rain streaks or raindrops of varying intensities. Recently many learning-based approaches have been proposed and achieved promising performance. However, these methods either focus on network architecture design or solely introduce image-level prior to the model. In this paper, we introduce text prior assisting the model in image deraining, as text descriptions have high flexibility and scalability. Text prior provides a wealth of semantic information to help the model achieve more detailed restoration, rather than blindly extrapolating details lost in the degraded image. To this end, we propose a novel image deraining framework based on the transformer, named TGDeraining. Specifically, to incorporate text prior into the framework, we design the Text Prior Embedded Transformer Block (TETB). TETB allows for dynamic guidance of the attention map guided by the text descriptions, thus emphasizing the restoration of critical missing details. The text prior is also fed to the feed-forward network to transform features in a controlled manner. Extensive experimental results demonstrate the effectiveness of our method in restoring a clear image using text as reference information.

To build an efficient unmanned aerial vehicle (UAV) fault diagnosis system, accurately modeling the relationship between sensor signals is a challenge. A common thought is to use a graph structure for modeling (Graph Neural Network), i.e., sensors as nodes and relationships between sensors are represented by edges. However, the Graph Neural Network (GNN) models, following the "Learning to Attend" principle, aim to maximize the mutual information between features and labels while minimizing training loss, without distinguishing the causal relationships between features and labels. The model’s lack of causal inference capability can lead to instability in model predictions, which ultimately shows up as a degradation in the model’s generalization performance on the test dataset. To address these issues, this paper proposes a GNN with causal learning to implement efficient UAV fault diagnosis, the model is called CLGNN. Specifically, the model first utilizes a GNN to model the sensor signals represented by the graph structure. Then, by intervening at the level of feature extraction, the non-causal components in the features are weakened to improve the model’s generalization performance in fault diagnosis. Extensive experimental results demonstrate that our method can robustly and accurately capture the anomalous signals of UAVs. In addition, we conduct a detailed analysis of the learned graphical representation of the sensor signals, exploring the decision-making basis of the model, which helps to boost the interpretability and reliability of the model.

Label distribution learning is a powerful learning paradigm to deal with label polysemy and has been widely applied in many practical tasks. A significant obstacle to the effective utilization of label distribution is the substantial expenses of accurate quantifying the label distributions. To tackle this challenge, label enhancement methods automatically infer label distributions from more easily accessible multi-label data based on binary annotations. However, the binary annotation of multi-label data requires experts to accurately assess whether each label can describe the instance, which may diminish the annotating efficiency and heighten the risk of erroneous annotation since the relationship between the label and the instance is unclear in many practical scenarios. Therefore, we propose to predict label distribution from ternary labels, allowing experts to annotate labels in a three-way annotation scheme. They can annotate the label as "$0$" indicating "uncertain relevant" if it is difficult to definitively determine whether the label can describe the instance, in addition to the binary annotation of "$1$" indicating "definitely relevant" and "$-1$" indicating "definitely irrelevant". Both the theoretical and methodological studies are conducted for the proposed learning paradigm. In the theoretical part, we conduct a quantitative comparison of approximation error between ternary and binary labels to elucidate the superiority of ternary labels over binary labels. In the methodological part, we propose a Categorical distribution with monotonicity and orderliness to model the mapping from label description degrees to ternary labels, which can serve as a loss function or as a probability distribution, allowing most existing label enhancement methods to be adapted to our task. Finally, we experimentally demonstrate the effectiveness of our proposal.

Label distribution learning (LDL) is a novel machine learning paradigm that aims to shift 0/1 labels into descriptive degrees to characterize the polysemy of instances. Since the description degree takes a value between 0 \ensuremath{\sim} 1, it is difficult for the annotator to accurately annotate each label. Therefore, the predictive ability of numerous LDL algorithms may be degraded by the presence of noise in the label space. To address this problem, we propose a novel stability-trust LDL framework that aims to reconstruct the feature space of an arbitrary LDL dataset by using feature decoupling and prototype guidance. Specifically, first, we use prototype learning to select reliable cluster centers (representative vectors of label distributions) to filter out a set of clean samples (with labeled noise) on the original dataset. Then, we decouple the feature space (eliminating correlations among features) by modeling a weight assigner that is learned on this clean sample set, thus assigning weights to each sample of the original dataset. Finally, all existing LDL algorithms can be trained on this new re-weighted dataset for the goal of robust modeling. In addition, we create a new image dataset to support the training and testing of compared models. Experimental results demonstrate that the proposed framework boosts the performance of the LDL algorithm on datasets with label noise.

Recently, large models (Segment Anything model) came on the scene to provide a new baseline for polyp segmentation tasks. This demonstrates that large models with a sufficient image level prior can achieve promising performance on a given task. In this paper, we unfold a new perspective on polyp segmentation modeling by leveraging the Depth Anything Model (DAM) to provide depth prior to polyp segmentation models. Specifically, the input polyp image is first passed through a frozen DAM to generate a depth map. The depth map and the input polyp images are then concatenated and fed into a convolutional neural network with multiscale to generate segmented images. Extensive experimental results demonstrate the effectiveness of our method, and in addition, we observe that our method still performs well on images of polyps with noise.

Haze severely affects the reliability of vision-based industrial systems, and most of the current dehazing methods are not applicable to images captured by ultra-high-definition (UHD) industrial cameras. In this article, we propose a novel dimensional transformation mixer (DMixer) model for recovering haze-free images from UHD haze images. In DMixer, the dimensional transformation module encodes the complete image in multiple stages from different perspectives and associates features from different views by permuting the tensor for efficient long-range dependency modeling. In this way, the global perception capabilities of DMixer are complemented, allowing the quality of the reconstructed UHD images to be improved. Furthermore, DMixer employs a dual-stream network framework that combines local and multiscale features, allowing DMixer to better trade off the performance and efficiency for real industrial systems. Our proposed method enables the real-time processing of UHD images ($\sim$59 fps). Extensive results show that the proposed model outperforms current state-of-the-art methods, with PSNR improvements of 1.94 and 0.95 dB on the 4KID and O-HAZE datasets, respectively.

Label distribution learning (LDL) is a novel machine-learning paradigm generalized from multilabel learning (MLL). LDL attaches a label distribution to each instance, giving the description degree of different labels. In many real-world applications, key labels, that is, labels with relatively higher description degrees, are preferable to be better predicted. Unfortunately, existing LDL metrics measure the distance or similarity between label distributions from a global perspective, failing to give sufficient attention to key labels. Therefore, we design a novel LDL metric, the description-degree percentile average (DPA), which simultaneously integrates both the exact ranking value and the description degree of each label. The DPA can enhance accuracy in predicting key labels. Furthermore, noting the shape characteristics of the label distributions, we minimize the variance distance between the predicted and the ground-truth label distributions, to better maintain the distinguishability of labels. Finally, we propose an adaptive weighted ranking-oriented LDL algorithm, which is more suitable for realistic LDL problems that require higher accuracy in predicting key labels. We conduct extensive comparison experiments on various types of LDL datasets. Experimental results on both traditional and newly introduced metrics demonstrate the effectiveness of our proposal.

Incomplete multiview clustering (IMVC) has received increasing attention since it is often that some views of samples are incomplete in reality. Most existing methods learn similarity subgraphs from original incomplete multiview data and seek complete graphs by exploring the incomplete subgraphs of each view for spectral clustering. However, the graphs constructed on the original high-dimensional data may be suboptimal due to feature redundancy and noise. Besides, previous methods generally ignored the graph noise caused by the interclass and intraclass structure variation during the transformation of incomplete graphs and complete graphs. To address these problems, we propose a novel joint projection learning and tensor decomposition (JPLTD)-based method for IMVC. Specifically, to alleviate the influence of redundant features and noise in high-dimensional data, JPLTD introduces an orthogonal projection matrix to project the high-dimensional features into a lower-dimensional space for compact feature learning. Meanwhile, based on the lower-dimensional space, the similarity graphs corresponding to instances of different views are learned, and JPLTD stacks these graphs into a third-order low-rank tensor to explore the high-order correlations across different views. We further consider the graph noise of projected data caused by missing samples and use a tensor-decomposition-based graph filter for robust clustering. JPLTD decomposes the original tensor into an intrinsic tensor and a sparse tensor. The intrinsic tensor models the true data similarities. An effective optimization algorithm is adopted to solve the JPLTD model. Comprehensive experiments on several benchmark datasets demonstrate that JPLTD outperforms the state-of-the-art methods. The code of JPLTD is available at https://github.com/weilvNJU/JPLTD.

In real applications, it is often that the collected multiview data contain missing views. Most existing incomplete multiview clustering (IMVC) methods cannot fully utilize the underlying information of missing data or sufficiently explore the consistent and complementary characteristics. In this article, we propose a novel Low-rAnk Tensor regularized viEws Recovery (LATER) method for IMVC, which jointly reconstructs and utilizes the missing views and learns multilevel graphs for comprehensive similarity discovery in a unified model. The missing views are recovered from a common latent representation, and the recovered views conversely improve the learning of shared patterns. Based on the shared subspace representations and recovered complete multiview data, the multilevel graphs are learned by self-representation to fully exploit the consistent and complementary information among views. Besides, a tensor nuclear norm regularizer is introduced to pursue the global low-rank property and explore the interview correlations. An alternating direction minimization algorithm is presented to optimize the proposed model. Moreover, a new initialization method is proposed to promote the effectiveness of our method for latent representation learning and missing data recovery. Extensive experiments demonstrate that our method outperforms the state-of-the-art approaches.

Label distribution learning (LDL) is an effective learning paradigm for dealing with label ambiguity. When applying LDL, the datasets annotated with label distributions (i.e., the real-valued vectors like the probability distribution) are typically required. Unfortunately, most existing datasets only contain the logical labels, and manual annotating with label distributions is costly. To address this problem, we treat the label distribution as a latent vector and infer its posterior by variational Bayes. Specifically, we propose a generative label enhancement model to encode the process of generating feature vectors and logical label vectors from label distributions in a principled way. In terms of features, we assume that the feature vector is generated by a Gaussian mixture dominated by the label distribution, which captures the one-to-many relationship from the label distribution to the feature vector and thus reduces the feature generation error. In terms of logical labels, we design a probability distribution to generate the logical label vector from a label distribution, which captures partial label ranking in the logical label vector and thus provides a more accurate guidance for inferring the label distribution. Besides, to approximate the posterior of the label distribution, we design a inference model, and derive the variational learning objective. Finally, extensive experiments on real-world datasets validate our proposal.

Label distribution is an effective label form to portray label polysemy (i.e., the cases that an instance can be described by multiple labels simultaneously). However, the expensive annotating cost of label distributions limits its application to a wider range of practical tasks. Therefore, LE (label enhancement) techniques are extensively studied to solve this problem. Existing LE algorithms mostly estimate label distributions by the instance relation or the label relation. However, they suffer from biased instance relations, limited model capabilities, or suboptimal local label correlations. Therefore, in this paper, we propose a deep generative model called JRC to simultaneously learn and cluster the joint implicit representations of both features and labels, which can be used to improve any existing LE algorithm involving the instance relation or local label correlations. Besides, we develop a novel label distribution recovery module, and then integrate it with JRC model, thus constituting a novel generative label enhancement model that utilizes the learned joint implicit representations and instance clusters in a principled way. Finally, extensive experiments validate our proposal.

The exposed cameras of UAVs can shake, shift, or even malfunction under the influence of harsh weather, while the add-on devices (Dupont lines) are very vulnerable to dam-age. Although we can place a low-cost transparent film overlay around the camera to protect it, this would also introduce image degradation issues (such as oversaturation, astigmatism, etc). To tackle the image degradation problem caused by overlaying transparent film, in this paper we propose a novel method to enhance the visual experience by adapting a deep network with UAV characteristics. Specifically, we propose a customized Transformer named UAVFormer to recover the image, which has a key module at each stage based on the Swin Transformer with local awareness (LAT). In the end, we use an evidential fusion algorithm to integrate the generated images at each stage to obtain a high-quality result. Furthermore, we create a high-resolution under-display camera dataset to support the training and testing of compared models. Our model can conduct high-quality recovery of images of 2K resolution on some embedded devices (Raspberry Pi 4b) in realtime. The URL for the code at https://github.com/zzr-idam/UAVFormer.

Label distribution offers more information about label polysemy than logical label. There are presently two approaches to obtaining label distributions: LDL (label distribution learning) and LE (label enhancement). In LDL, experts must annotate training instances with label distributions, and a predictive function is trained on this training set to obtain label distributions. In LE, experts must annotate instances with logical labels, and label distributions are recovered from them. However, LDL is limited by expensive annotations, and LE has no performance guarantee. Therefore, we investigate how to predict label distribution from TMLR (tie-allowed multi-label ranking) which is a compromise on annotation cost but has good performance guarantees. On the one hand, we theoretically dissect the relationship between TMLR and label distribution. We define EAE (expected approximation error) to quantify the quality of an annotation, provide EAE bounds for TMLR, and derive the optimal range of label distributions corresponding to a given TMLR annotation. On the other hand, we propose a framework for predicting label distribution from TMLR via conditional Dirichlet mixtures. This framework blends the procedures of recovering and learning label distributions end-to-end and allows us to effortlessly encode our knowledge by a semi-adaptive scoring function. Extensive experiments validate our proposal.

The ever-growing aging population has led to an increasing need for removable partial dentures (RPDs) since they are typically the least expensive treatment options for partial edentulism. However, the digital design of RPDs remains challenging for dental technicians due to the variety of partially edentulous scenarios and complex combinations of denture components. To accelerate the design of RPDs, we propose a U-shape network incorporated with Transformer blocks to automatically generate RPD clasps, one of the most frequently used RPD components. Unlike existing dental restoration design algorithms, we introduce the voxel-based truncated signed distance field (TSDF) as an intermediate representation, which reduces the sensitivity of the network to resolution and contributes to more smooth reconstruction. Besides, a selective insertion scheme is proposed for solving the memory issue caused by Transformer blocks and enables the algorithm to work well in scenarios with insufficient data. We further design two weighted loss functions to filter out the noisy signals generated from the zero-gradient areas in TSDF. Ablation and comparison studies demonstrate that our algorithm outperforms state-of-the-art reconstruction methods by a large margin and can serve as an intelligent auxiliary in denture design.

Label distribution learning (LDL) is a novel machine learning paradigm that gives a description degree of each label to a particular instance. But many existing datasets contain only simple logical labels, since it is difficult and time-consuming to directly obtain the label distribution. So label enhancement (LE) is proposed to convert multi-label datasets consisting of logical labels into label distribution datasets. In recently, many LE algorithms have been proposed and most of them concentrate on the fitting degree, but ignore the ordering relation between positive and negative labels. Therefore, in this paper, we propose an LE algorithm based on maintaining positive and negative label relation, which contains a novel ranking loss that can generate different penalties according to different ranking errors. Our algorithm achieves a good balance between the degree of fitting and the ordering relation. The experimental results on several real-world datasets validate the effectiveness of our method.

Label distribution learning (LDL) is a novel machine learning paradigm that can be seen as an extension of multi-label learning (MLL). Compared with MLL, the advantages of LDL are reflected in the following perspectives: (1) the label distribution gives the relevance description of each label to unknown instances in quantitative terms; (2) the distribution implicitly gives the relevance intensities relation of different labels to a particular instance in qualitative terms, i.e., the label ranking relation. All existing LDL models aim to fit the ground-truth label distribution by quantitatively minimizing the distance between distributions or maximizing the similarity between distributions, which only uses the first advantage of the label distribution but ignores the label ranking relation, which may lose some useful semantic information implied in the label distribution, thus reducing the performance of LDL. Therefore, we propose a novel algorithm to solve this problem by introducing the ranking loss function to LDL. In addition, in order to evaluate the LDL algorithms more comprehensively and verify that the ranking loss is beneficial for keeping the label ranking relation, we also introduce two popular ranking evaluation metrics for LDL. The experimental results on 13 real-world datasets validate the effectiveness of our method.

Hashing methods have captured much attention for cross-modal retrieval in recent years. Most existing approaches mainly focus on preserving the semantic similarity across heterogeneous modalities in a shared Hamming subspace, while the label information and potential correlations of multi-label semantics are not fully excavated. In this article, a novel Adaptive Label correlation based asymmEtric Cross-modal Hashing method, i.e., ALECH, is proposed for cross-modal retrieval. ALECH decomposes hash learning into two steps, hash codes learning and hash functions learning. For hash codes learning, the high-order semantic label correlations are adaptively exploited to guide the latent feature learning, while simultaneously generating the binary codes in a discrete manner. The asymmetric strategy is utilized to connect the latent feature space and Hamming space, and preserve the pairwise semantic similarity. Different from other two-step methods that directly adopt simple least-squares regression to learn hash functions based on binary codes, ALECH leverages both hash codes and semantic labels for hash functions learning which further preserves the similarity. Experiments on several benchmark datasets demonstrate that the proposed ALECH method outperforms the state-of-the-art cross-hashing methods.

In recent years, Cross-Modal Hashing (CMH) has attracted much attention due to its fast query speed and efficient storage. Previous studies have achieved promising results for Cross-Modal Retrieval (CMR) by discovering discriminative hash codes and modality-specific hash functions. Nonetheless, most existing CMR works are subjected to some restrictions: 1) It is assumed that data of different modalities are fully paired, which is impractical in real applications due to sample missing and false data alignment, and 2) binary regression targets including the label matrix and binary codes are too rigid to effectively learn semantic-preserving hash codes and hash functions. To address these problems, this paper proposes an Adaptive Marginalized Semantic Hashing (AMSH) method which not only enhances the discrimination of latent representations and hash codes by adaptive margins, but can also be used for both paired and unpaired CMR. As a two-step method, in the first step, AMSH generates semantic-aware modality-specific latent representations with adaptively marginalized labels, thereby enlarging the distances between different classes, and exploiting the labels to preserve the inter-modal and intra-modal semantic similarities into latent representations and hash codes. In the second step, adaptive margin matrices are embedded into the hash codes, and enlarge the gaps between positive and negative bits, which improves the discrimination and robustness of hash functions. On this basis, AMSH generates similarity-preserving hash codes and robust hash functions without the strict one-to-one data correspondence requirement. Experiments are conducted on several benchmark datasets to demonstrate the superiority and flexibility of AMSH over some state-of-the-art CMR methods. The source code is available athttps://github.com/LKYLKYZ/AMSH.

Label distribution can provide richer information about label polysemy than logical labels in multi-label learning. There are currently two strategies including LDL (label distribution learning) and LE (label enhancement) to predict label distributions. LDL requires experts to annotate instances with label distributions and learn a predictive mapping on such a training set. LE requires experts to annotate instances with logical labels and generates label distributions from them. However, LDL requires costly annotation, and the performance of the LE is unstable. In this paper, we study the problem of predicting label distribution from multi-label ranking which is a compromise w.r.t. annotation cost but has good guarantees for performance. On the one hand, we theoretically investigate the relation between multi-label ranking and label distribution. We define the notion of EAE (expected approximation error) to quantify the quality of an annotation, give the bounds of EAE for multi-label ranking, and derive the optimal range of label distribution corresponding to a particular multi-label ranking. On the other hand, we propose a framework of label distribution predicting from multi-label ranking via conditional Dirichlet mixtures. This framework integrates the processes of recovering and learning label distributions end-to-end and allows us to easily encode our knowledge about current tasks by a scoring function. Finally, we implement extensive experiments to validate our proposal.

Optimization modeling of real-world application problems usually involves noise from various sources. Noisy optimization imposes challenges to optimization methods since the objective values can be different for multiple evaluations. In this article, we propose a novel online population size learning (OPL) technique of evolution strategies for handling noisy optimization problems. By re-evaluating a fraction of the candidates, we measure the strength of noise level of the re-evaluated candidate solutions and adapt the population size according to the noise level. The proposed OPL combines the advantages of both explicit averaging by re-evaluations and the implicit averaging by large population size and overcomes their limitations. We incorporate it with the covariance matrix adaptation evolution strategy (CMA-ES) and obtain OPL-CMA-ES. Compared with the existing noise handling technique, the proposed OPL is much simpler in both concepts and computation. We conduct comprehensive experiments to evaluate the algorithm’s performance on standard problems with Gaussian noise. We further evaluate the performance of OPL-CMA-ES on the black-box optimization benchmarks (BBOBs) noisy testbed, which is a standard platform for comparing black-box optimization algorithms, compared with the state-of-the-art noise-handling algorithms. The experimental results show that OPL-CMA-ES achieves remarkable performance and outperforms the compared variants.

Convolutional neural networks (CNNs) have achieved significant success in the single image dehazing task. Unfortunately, most existing deep dehazing models have high computational complexity, which hinders their application to high-resolution images, especially for UHD (ultra-high-definition) or 4K resolution images. To address the problem, we propose a novel network capable of real-time dehazing of 4K images on a single GPU, which consists of three deep CNNs. The first CNN extracts haze-relevant features at a reduced resolution of the hazy input and then fits locally-affine models in the bilateral space. Another CNN is used to learn multiple full-resolution guidance maps corresponding to the learned bilateral model. As a result, the feature maps with high-frequency can be reconstructed by multi-guided bilateral upsampling. Finally, the third CNN fuses the high-quality feature maps into a dehazed image. In addition, we create a large-scale 4K image dehazing dataset to support the training and testing of compared models. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art dehazing approaches on various benchmarks.

Existing single image high dynamic range (HDR) reconstruction methods attempt to expand the range of illuminance. They are not effective in generating plausible textures and colors in the reconstructed results, especially for high-density pixels in ultra-high-definition (UHD) images. To address these problems, we propose a new HDR reconstruction network for UHD images by collaboratively learning color and texture details. First, we propose a dual-path network to extract the content and chromatic features at a reduced resolution of the low dynamic range (LDR) input. These two types of features are used to fit bilateral-space affine models for real-time HDR reconstruction. To extract the main data structure of the LDR input, we propose to use 3D Tucker decomposition and reconstruction to prevent pseudo edges and noise amplification in the learned bilateral grid. As a result, the high-quality content and chromatic features can be reconstructed capitalized on guided bilateral upsampling. Finally, we fuse these two full-resolution feature maps into the HDR reconstructed results. Our proposed method can achieve real-time processing for UHD images (about 160 fps). Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art HDR reconstruction approaches on public benchmarks and real-world UHD images.

Label distribution learning (LDL) is proposed for solving the label ambiguity problem in recent years, which can be seen as an extension of multi-label learning. To improve the performance of label distribution learning, some existing algorithms exploit label correlations in a global manner that assumes the label correlations are shared by all instances. However, the instances in different groups may share different label correlations, and few label correlations are globally applicable in real-world tasks. In this paper, two novel label distribution learning algorithms are proposed by exploiting label correlations on local samples, which are called GD-LDL-SCL and Adam-LDL-SCL, respectively. To utilize the label correlations on local samples, the influence of local samples is encoded, and a local correlation vector is designed as the additional features for each instance, which is based on the different clustered local samples. Then, the label distribution for an unseen instance can be predicted by exploiting the original features and the additional features simultaneously. Extensive experiments on some real-world data sets validate that our proposed methods can address the label distribution problems effectively and outperform state-of-the-art methods.

Label enhancement (LE) is a procedure of recovering the label distributions from the logical labels in the multi-label data, the purpose of which is to better represent and mine the label ambiguity problem through the form of label distribution. Existing LE work mainly concentrates on how to leverage the topological information of the feature space and the correlation among the labels, and all are based on single view data. In view of the fact that there are many multi-view data in real-world applications, which can provide richer semantic information from different perspectives, this paper first presents a multi-view label enhancement problem and proposes a tensor-based multi-view label enhancement method, named TMV-LE. Firstly, we introduce the tensor factorization to get the common subspace which contains the high-order relationships among different views. Secondly, we use the common representation and multiple views to jointly mine a more comprehensive topological structure in the dataset. Finally, the topological structure of the feature space is migrated to the label space to get the label distributions. Extensive comparative studies validate that the performance of multi-view multi-label learning can be improved significantly with TMV-LE.

Label distribution learning has attracted more and more attention in view of its more generalized ability to express the label ambiguity. However, it is much more expensive to obtain the label distribution information of the data rather than the logical labels. Thus, label enhancement is proposed to recover the label distributions from the logical labels. In this paper, we propose a novel label enhancement method by using privileged information. We first apply a multi-label learning model to implicitly capture the complex structural information between instances and generate the privileged information. Second, we adopt LUPI (learning with privileged information) paradigm to utilize the privileged information and employ RSVM+ as the prediction model. Finally, comparison experiments on 12 datasets demonstrate that our proposal can better fit the ground-truth label distributions.

Multi-label learning has been successfully applied to solve instance multi-semantics problems. Moreover, the topology information of samples is often adopted in existing works to improve the prediction performance, in which the similarity of samples is usually calculated in the entire feature space. However, in real-world applications, each label is often determined by a subset of the original features, so when we focus on different labels, the similarity of two instances may be different. In this paper, we propose a multi-label learning method by exploiting the local similarity of samples. Specifically, the smoothness assumption is applied to assume that if the feature subset is similar between samples, the corresponding label should be similar. In addition, L1 regularization is also adopted to sparse the weight coefficients when constraining the output space of the instance. The experimental results on several data sets validate the effectiveness of the proposed method.

Emotion recognition from facial expressions is an interesting and challenging problem and has attracted much attention in recent years. Substantial previous research has only been able to address the ambiguity of “what describes the expression”, which assumes that each facial expression is associated with one or more predefined affective labels while ignoring the fact that multiple emotions always have different intensities in a single picture. Therefore, to depict facial expressions more accurately, this paper adopts a label distribution learning approach for emotion recognition that can address the ambiguity of “how to describe the expression” and proposes an emotion distribution learning method that exploits label correlations locally. Moreover, a local low-rank structure is employed to capture the local label correlations implicitly. Experiments on benchmark facial expression datasets demonstrate that our method can better address the emotion distribution recognition problem than state-of-the-art methods.

Label distribution learning (LDL) is a novel machine learning paradigm to deal with label ambiguity issues by placing more emphasis on how relevant each label is to a particular instance. Many LDL algorithms have been proposed and most of them concentrate on the learning models, while few of them focus on the feature selection problem. All existing LDL models are built on a simple feature space in which all features are shared by all the class labels. However, this kind of traditional data representation strategy tends to select features that are distinguishable for all labels, but ignores label-specific features that are pertinent and discriminative for each class label. In this paper, we propose a novel LDL algorithm by leveraging label-specific features. The common features for all labels and specific features for each label are simultaneously learned to enhance the LDL model. Moreover, we also exploit the label correlations in the proposed LDL model. The experimental results on several real-world data sets validate the effectiveness of our method.

Label distribution learning (LDL) can be viewed as the generalization of multi-label learning. This novel paradigm focuses on the relative importance of different labels to a particular instance. Most previous LDL methods either ignore the correlation among labels, or only exploit the label correlations in a global way. In this paper, we utilize both the global and local relevance among labels to provide more information for training model and propose a novel label distribution learning algorithm. In particular, a label correlation matrix based on low-rank approximation is applied to capture the global label correlations. In addition, the label correlation among local samples are adopted to modify the label correlation matrix. The experimental results on real-world data sets show that the proposed algorithm outperforms state-of-the-art LDL methods.

Label distribution learning (LDL) is a newly arisen machine learning method that has been increasingly studied in recent years. In theory, LDL can be seen as a generalization of multi-label learning. Previous studies have shown that LDL is an effective approach to solve the label ambiguity problem. However, the dramatic increase in the number of possible label sets brings a challenge in performance to LDL. In this paper, we propose a novel label distribution learning algorithm to address the above issue. The key idea is to exploit correlations between different labels. We encode the label correlation into a distance to measure the similarity of any two labels. Moreover, we construct a distance-mapping function from the label set to the parameter matrix. Experimental results on eight real label distributed data sets demonstrate that the proposed algorithm performs remarkably better than both the state-of-the-art LDL methods and multi-label learning methods.

Label distribution learning (LDL) is a novel multi-label learning paradigm proposed in recent years for solving label ambiguity. Existing approaches typically exploit label correlations globally to improve the effectiveness of label distribution learning, by assuming that the label correlations are shared by all instances. However, different instances may share different label correlations, and few correlations are globally applicable in real-world applications. In this paper, we propose a new label distribution learning algorithm by exploiting sample correlations locally (LDL-SCL). To encode the influence of local samples, we design a local correlation vector for each instance based on the clustered local samples. Then we predict the label distribution for an unseen instance based on the original features and the local correlation vector simultaneously. Experimental results demonstrate that LDL-SCL can effectively deal with the label distribution problems and perform remarkably better than the state-of-the-art LDL methods.

Image segmentation is an important issue in computer vision. The methods based on Fuzzy C-Means (FCM) algorithms have gained success. However, these approaches deal with each pixel as a separate object, which will ignore the spatial information among these pixels. This paper proposes an approach which combines the Fuzzy C-Means algorithm and Graph Cut Theory both for gray and color image segmentation. We adopt the Turbopixel algorithm to split the color image into varied small regions called superpixels for presegmentation and extract color histogram features from the superpixels. Based on color histogram feature, we use FCM to make the original clusters. Then we build a graph model, and use maximum flow algorithm to get the minimum cut, namely the initial segmentation result of the image. Finally, we use a recursive process to achieve the result of image segmentation. The key point of our approach is building a great graphical model and utilizing the existing binary segmentation model to solve the multi-value segmentation. Experimental results show that our approach can obtain good segmentation results comparing with FCM only under different parameters setup and binary segmentation.