Set Of Labels Research Articles

The Image of the Arab World in the Spanish and Latin American Journalistic Discourse: Immigration as an Example

Spain's and Latin America's perception of Arabs is conditioned by a set of labels. This article aims to study the (re)presentation of the figure of the Arab immigrant in both Spanish and Latin American journalistic discourse. The researchers, through the use of a series of lexical and rhetorical resources, demonstrate that, this discourse effectively contributes to the generation of labels about the population of the study in question. Our corpus of analysis is essentially made up of newspaper articles with national and local circulation (El Mundo, El Diario de Sevilla, El Tiempo, Libertad Digital, etc.). The methodology followed in the analysis is based on the theories of Van Dijk about discourse and racism in Spain and Latin America.

Integral sum graphs Gn and G-r,n are perfect graphs

A graph G is an integral sum graph (sum graph) if its vertices can be labeled with distinct integers (positive integers) so that e = uv is an edge of G if and only if the sum of the labels on vertices u and v is also a label in G. A graph G is perfect if the chromatic number of each of its induced subgraphs is equal to the clique number of the same. A simple graph G is of class 1 if its edge chromatic number and maximum degree are same. In this paper, we prove that integral sum graphs Gn , G 0 , n and G − r , n over the label sets [ 1 , n ] , [ 0 , n ] and [ − r , n ] , respectively, are perfect graphs as well as of class 1 for r , n ∈ N . We also obtain a few structural properties of these graphs.

A Numerically Exact Algorithm for the Bin-Packing Problem

We propose a numerically exact algorithm for solving the Bin-Packing Problem (BPP) based on a branch-price-and-cut framework combined with a pattern-enumeration method. Key to the algorithm is a novel technique for the computation of numerically safe dual bounds for the widely adopted set covering reformulation of the BPP (tightened with additional valid inequalities) with a precision that is higher than the one of general-purpose floating-point solvers. Our branch-price-and-cut algorithm also relies on an exact integer (fixed-point) label setting algorithm for solving the pricing problem associated with the tightened set-covering formulation. To the best of our knowledge, ours is the first algorithm for the BPP that is numerically exact and practical for solving large-scale instances. Extensive computational results on instances affected by notorious numerical difficulties (those of the Augmented Non-IRUP class) show that our exact algorithm outperforms all of the not numerically exact state-of-the-art algorithms based on branch-and-cut-and-price techniques that rely on a set-covering formulation of the BPP. History: Accepted by Andrea Lodi, Area Editor for Design & Analysis of Algorithms − Discrete.

3D detection transformer: Set prediction of objects using point clouds

Object detection in 3D scenes rely on two main methods: detection based on proposals (two-stage detectors) or detections based on anchors (single-stage detectors), similar to approaches for object detection in 2D. In this paper, we propose the 3DeTR framework that produces 3D detections without the use of anchors or proposals, allowing training of the entire neural network in an end-to-end manner. Raw point cloud scenes are augmented and input into distance-and-reflectiveness-based feature extractor to produce representative points. Then, a transformer encoder–decoder module learns the local object relations and global context to generate parallel detections, which are then passed to a set-based loss function to map predictions to the set of ground truth labels uniquely. The model’s architecture produces 3D detections by regressing directly with the set of ground truths without the need for anchors or proposals, which are bottlenecks for object detection performances. We tested the framework on the KITTI Vision Benchmark Suite 3D object detection dataset, achieving results on par with the state-of-the-art: 80.37 AP on Cars (Moderate) class and 47.92 AP on Pedestrians (Moderate) class.

Improving Graph Neural Networks by combining active learning with self-training

In this paper, we propose a novel framework, called STAL, which makes use of unlabeled graph data, through a combination of Active Learning and Self-Training, in order to improve node labeling by Graph Neural Networks (GNNs). GNNs have been shown to perform well on many tasks, when sufficient labeled data are available. Such data, however, is often scarce, leading to the need for methods that leverage unlabeled data that are abundant. Active Learning and Self-training are two common approaches towards this goal and we investigate here their combination, in the context of GNN training. Specifically, we propose a new framework that first uses active learning to select highly uncertain unlabeled nodes to be labeled and be included in the training set. In each iteration of active labeling, the proposed method expands also the label set through self-training. In particular, highly certain pseudo-labels are obtained and added automatically to the training set. This process is repeated, leading to good classifiers, with a limited amount of labeled data. Our experimental results on various datasets confirm the efficiency of the proposed approach.

Progressive Enhancement of Label Distributions for Partial Multilabel Learning.

Partial multi-label learning (PML) aims to learn a multilabel predictive model from the PML training examples, each of which is associated with a set of candidate labels where only a subset is valid. The common strategy to induce a predictive model is identifying the valid labels in each candidate label set. Nonetheless, this strategy ignores considering the essential label distribution corresponding to each instance as label distributions are not explicitly available in the training dataset. In this article, a novel partial multilabel learning method is proposed to recover the latent label distribution and progressively enhance it for predictive model induction. Specifically, the label distribution is recovered by considering the observation model for logical labels and the sharing topological structure from feature space to label distribution space. Besides, the latent label distribution is progressively enhanced by recovering latent labeling information and supervising predictive model training alternatively to make the label distribution appropriate for the induced predictive model. Experimental results on PML datasets clearly validate the effectiveness of the proposed method for solving partial multilabel learning problems. In addition, further experiments show the high quality of the recovered label distributions and the effectiveness of adopting label distributions for partial multilabel learning.

Incorporating keyword extraction and attention for multi-label text classification

As one of the fundamental tasks in natural language processing, Multi-Label Text Classification (MLTC) is used to mark one or more relevant labels for a given text from a large set of labels. Existing MLTC methods have increasingly focused on improving classification effectiveness by fusing the correlations of labels. Still, the research suffers from difficulties in comprehensively extracting text features and distinguishing similar labels. This paper proposed a multi-label text classification model based on keyword extraction and attention mechanism. The model proposed using keywords to represent labels, adopting both self-attention and interactive attention mechanisms (between labels and text) to extract text features and create text vectors. Finally, fusing text vectors as the classifier’s input. Experiments were conducted on two public datasets and a self-built dataset of illegal advertisements. The experimental results showed that the keyword-based label representation approach proposed in this paper can better obtain label semantics, avoid noise and improve the performance of the multi-label text classification.

Discriminative Metric Learning for Partial Label Learning.

One simple strategy to deal with ambiguity in partial label learning (PLL) is to regard all candidate labels equally as the ground-truth label, and then solve the PLL problem using existing multiclass classification algorithms. However, due to the noisy false-positive labels in the candidate set, these approaches are readily mislead and do not generalize well in testing. Consequently, the method of identifying the ground-truth label straight from the candidate label set has grown popular and effective. When the labeling information in PLL is ambiguous, we ought to take advantage of the data's underlying structure, such as label and feature interdependencies, to conduct disambiguation. Furthermore, while metric learning is an excellent method for supervised learning classification that takes feature and label interdependencies into account, it cannot be used to solve the weekly supervised learning PLL problem directly due to the ambiguity of labeling information in the candidate label set. In this article, we propose an effective PLL paradigm called discriminative metric learning for partial label learning (DML-PLL), which aims to learn a Mahanalobis distance metric discriminatively while identifying the ground-truth label iteratively for PLL. We also design an efficient algorithm to alternatively optimize the metric parameter and the latent ground-truth label in an iterative way. Besides, we prove the convergence of the designed algorithms by two proposed lemmas. We additionally study the computational complexity of the proposed DML-PLL in terms of training and testing time for each iteration. Extensive experiments on both controlled UCI datasets and real-world PLL datasets from diverse domains demonstrate that the proposed DML-PLL regularly outperforms the compared approaches in terms of prediction accuracy.

Compositional clustering: Applications to multi-label object recognition and speaker identification

We consider a novel clustering task in which clusters can have compositional relationships, e.g., one cluster contains images of rectangles, one contains images of circles, and a third (compositional) cluster contains images with both objects. In contrast to hierarchical clustering in which a parent cluster represents the intersection of properties of the child clusters, our problem is about finding compositional clusters that represent the union of the properties of the constituent clusters. This task is motivated by recently developed few-shot learning and embedding models (Alfassy et al., 2019; Li et al., 2021) that can distinguish the label sets, not just the individual labels, assigned to the examples. We propose three new algorithms – Compositional Affinity Propagation (CAP), Compositional k-means (CKM), and Greedy Compositional Reassignment (GCR) – that can partition examples into coherent groups and infer the compositional structure among them. We show promising results, compared to popular algorithms such as Gaussian mixtures, Fuzzy c-means, and Agglomerative Clustering, on the OmniGlot and LibriSpeech datasets. Our work has applications to open-world multi-label object recognition and speaker identification & diarization with simultaneous speech from multiple speakers.

Climatology and decadal changes of Arctic atmospheric rivers based on ERA5 and MERRA-2

We present the Arctic atmospheric river (AR) climatology based on twelve sets of labels derived from ERA5 and MERRA-2 reanalyses for 1980–2019. The ARs were identified and tracked in the 3-hourly reanalysis data with a multifactorial approach based on either atmospheric column-integrated water vapor (IWV) or integrated water vapor transport (IVT) exceeding one of the three climate thresholds (75th, 85th, and 95th percentiles). Time series analysis of the AR event counts from the AR labels showed overall upward trends from the mid-1990s to 2019. The 75th IVT- and IWV-based labels, as well as the 85th IWV-based labels, are likely more sensitive to Arctic surface warming, therefore, detected some broadening of AR-affected areas over time, while the rest of the labels did not. Spatial exploratory analysis of these labels revealed that the AR frequency of occurrence maxima shifted poleward from over-land in 1980–1999 to over the Arctic Ocean and its outlying Seas in 2000–2019. Regions across the Atlantic, the Arctic, to the Pacific Oceans trended higher AR occurrence, surface temperature, and column-integrated moisture. Meanwhile, ARs were increasingly responsible for the rising moisture transport into the Arctic. Even though the increase of Arctic AR occurrence was primarily associated with long-term Arctic surface warming and moistening, the effects of changing atmospheric circulation could stand out locally, such as on the Pacific side over the Chukchi Sea. The changing teleconnection patterns strongly modulated AR activities in time and space, with prominent anomalies in the Arctic-Pacific sector during the latest decade. Besides, the extreme events identified by the 95th-percentile labels displayed the most significant changes and were most influenced by the teleconnection patterns. The twelve Arctic AR labels and the detailed graphics in the atlas can help navigate the uncertainty of detecting and quantifying Arctic ARs and their associated effects in current and future studies.

Targeted multiobjective Dijkstra algorithm

We introduce the Targeted Multiobjective Dijkstra Algorithm (T‐MDA), a label setting algorithm for the One‐to‐One Multiobjective Shortest Path (MOSP) Problem. It is based on the recently published Multiobjective Dijkstra Algorithm (MDA) and equips it with A*‐like techniques. For any explored subpath, a label setting MOSP algorithm decides whether the subpath can be discarded or must be stored as part of the output. A major design choice is how to store subpaths from the moment they are first explored until the mentioned final decision can be made. The T‐MDA combines the polynomially bounded size of the priority queue used in the MDA and a lazy management of paths that are not in the queue. The running time bounds from the MDA remain valid. In practice, the T‐MDA outperforms known algorithms from the literature and the increased memory consumption is negligible. In this paper, we benchmark the T‐MDA against an improved version of the state of the art One‐to‐One MOSP algorithm from the literature on a standard testbed.

Partial Domain Adaptation Without Domain Alignment.

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a related and unlabeled target domain with identical label space. The main workhorse in UDA is domain alignment and has proven successful. However, it is practically difficult to find an appropriate source domain with identical label space. A more practical scenario is partial domain adaptation (PDA) where the source label space subsumes the target one. Unfortunately, due to the non-identity between label spaces, it is extremely hard to obtain an ideal alignment, conversely, easier resulting in mode collapse and negative transfer. These motivate us to find a relatively simpler alternative to solve PDA. To achieve this, we first explore a theoretical analysis, which says that the target risk is bounded by both model smoothness and between-domain discrepancy. Then, we instantiate the model smoothness as an intra-domain structure preserving (IDSP) while giving up possibly riskier domain alignment. To our best knowledge, this is the first naive attempt for PDA without alignment. Finally, our empirical results on benchmarks demonstrate that IDSP is not only superior to the PDA SOTAs (e.g., ∼+10% on Cl → Rw and ∼+8% on Ar → Rw), but also complementary to domain alignment in the standard UDA.

Dual-View Noise Correction for Crowdsourcing

In crowdsourcing scenarios, each instance obtains a multiple noisy label set from different crowd workers on the Internet and then gets its integrated label via label integration. Although label integration algorithms are often effective, a certain level of noise still remains in the integrated labels. To reduce the impact of noise on label quality, many noise correction algorithms have been proposed in recent years. However, most of them are hard to fully utilize the joint information of the original attribute view and multiple noisy label view. Motivated by multi-view learning, in this paper, we propose a dual-view noise correction (DVNC) algorithm. Benefiting from the complementary and consensus principle, DVNC can fully utilize the joint information of two views and thus enhance the effect of noise correction. In DVNC, we at first construct the original attribute view and multiple noisy label view for each instance and respectively train a classifier on each view. Then, we use the trained two classifiers to filter each noise instance and thus obtain a clean set and noise set. Finally, we train a classifier on the clean set to correct each instance in the noise set via reclassifying it as the class with the maximum posterior probability. The experimental results on simulated and real-world datasets indicate that DVNC significantly outperforms all the other noise correction algorithms used for comparison.

Multi-graph multi-label learning with novel and missing labels

Real-life objects typically contain complex structures, and the graph is a prevalent presentation for describing such objects. Multi-graph multi-label (MGML) learning is a supervised learning framework for learning complicated objects associated with multiple labels, where each object is described as a bag-of-graphs representation. However, existing methods are dependent on transforming graphs into instances, which prevents the structure information from being fully utilized; in addition, the adaptability of MGML is insufficient for the assumptions that the label set is in a closed environment and complete. In real applications, some novel labels may exist outside the fixed set, and some values of labels are missing. Existing MGML approaches are unable to deal with these novel and missing labels. In this paper, we propose a new multi-graph multi-label learning with novel and missing labels (Mgmlnm) algorithm, which is the first attempt to learn novel and missing labels in the MGML problem. To preserve the structure information, we exploit the specific graph kernels to generate an efficient graph representation. To learn multi-graph data with novel and missing labels, we propose a unified objective function, which has a two-perspective regularization term, a projection-similarity regularization term, and a bag-dependent regularization term, enabling novel and missing labels to be modeled simultaneously and exploring the complex relationship between bag and graph labels. Two first-order proximity optimization methods are then developed to solve the unified problem efficiently. A theoretical analysis of the generalization bound is provided for the unified objective. Experimental results demonstrate the effectiveness of the proposed algorithm.

Mirror complementary transformer network for RGB‐thermal salient object detection

AbstractConventional RGB‐T salient object detection treats RGB and thermal modalities equally to locate the common salient regions. However, the authors observed that the rich colour and texture information of the RGB modality makes the objects more prominent compared to the background; and the thermal modality records the temperature difference of the scene, so the objects usually contain clear and continuous edge information. In this work, a novel mirror‐complementary Transformer network (MCNet) is proposed for RGB‐T SOD, which supervise the two modalities separately with a complementary set of saliency labels under a symmetrical structure. Moreover, the attention‐based feature interaction and serial multiscale dilated convolution (SDC)‐based feature fusion modules are introduced to make the two modalities complement and adjust each other flexibly. When one modality fails, the proposed model can still accurately segment the salient regions. To demonstrate the robustness of the proposed model under challenging scenes in real world, the authors build a novel RGB‐T SOD dataset VT723 based on a large public semantic segmentation RGB‐T dataset used in the autonomous driving domain. Extensive experiments on benchmark and VT723 datasets show that the proposed method outperforms state‐of‐the‐art approaches, including CNN‐based and Transformer‐based methods. The code and dataset can be found at https://github.com/jxr326/SwinMCNet.

Three-way decision-based noise correction for crowdsourcing

In crowdsourcing learning, a certain degree of label noise still exists in the integrated labels, which are obtained by label integration algorithms. In order to decrease the impact of label noise, many scholars focus on noise correction algorithms. Existing noise correction algorithms usually divide a data set with integrated labels into a clean set and a noise set, directly. However, there are certain noise instances in the clean set and clean instances in the noise set. To reduce the interference from noise instances and improve the utilization of clean instances, inspired by the three-way decision theory, we propose a three-way decision-based noise correction (TDNC) algorithm. Firstly, we calculate the compactness of each instance's multiple noisy label set and estimate the label certainty of each instance's integrated label. Secondly, we divide a data set with integrated labels into three disjoint sets, called positive set, boundary set and negative set, respectively. Thirdly, we further divide and add the instances in the boundary set into the positive set and the negative set according to the nearest neighbor classification. Finally, we train two heterogeneous classifiers on the new positive set to correct the noise instances in the new negative set using a consensus voting strategy. The experimental results on 34 simulated and two real-world data sets consistently show that TDNC significantly outperforms the existing state-of-the-art noise correction algorithms in terms of the noise ratio.

Partial-Label Regression

Partial-label learning is a popular weakly supervised learning setting that allows each training example to be annotated with a set of candidate labels. Previous studies on partial-label learning only focused on the classification setting where candidate labels are all discrete, which cannot handle continuous labels with real values. In this paper, we provide the first attempt to investigate partial-label regression, where each training example is annotated with a set of real-valued candidate labels. To solve this problem, we first propose a simple baseline method that takes the average loss incurred by candidate labels as the predictive loss. The drawback of this method lies in that the loss incurred by the true label may be overwhelmed by other false labels. To overcome this drawback, we propose an identification method that takes the least loss incurred by candidate labels as the predictive loss. We further improve it by proposing a progressive identification method to differentiate candidate labels using progressively updated weights for incurred losses. We prove that the latter two methods are model-consistent and provide convergence analysis showing the optimal parametric convergence rate. Our proposed methods are theoretically grounded and can be compatible with any models, optimizers, and losses. Experiments validate the effectiveness of our proposed methods.

Label-Specific Feature Augmentation for Long-Tailed Multi-Label Text Classification

Multi-label text classification (MLTC) involves tagging a document with its most relevant subset of labels from a label set. In real applications, labels usually follow a long-tailed distribution, where most labels (called as tail-label) only contain a small number of documents and limit the performance of MLTC. To facilitate this low-resource problem, researchers introduced a simple but effective strategy, data augmentation (DA). However, most existing DA approaches struggle in multi-label settings. The main reason is that the augmented documents for one label may inevitably influence the other co-occurring labels and further exaggerate the long-tailed problem. To mitigate this issue, we propose a new pair-level augmentation framework for MLTC, called Label-Specific Feature Augmentation (LSFA), which merely augments positive feature-label pairs for the tail-labels. LSFA contains two main parts. The first is for label-specific document representation learning in the high-level latent space, the second is for augmenting tail-label features in latent space by transferring the documents second-order statistics (intra-class semantic variations) from head labels to tail labels. At last, we design a new loss function for adjusting classifiers based on augmented datasets. The whole learning procedure can be effectively trained. Comprehensive experiments on benchmark datasets have shown that the proposed LSFA outperforms the state-of-the-art counterparts.

Knowledge Amalgamation for Multi-Label Classification via Label Dependency Transfer

Multi-label classification (MLC), which assigns multiple labels to each instance, is crucial to domains from computer vision to text mining. Conventional methods for MLC require huge amounts of labeled data to capture complex dependencies between labels. However, such labeled datasets are expensive, or even impossible, to acquire. Worse yet, these pre-trained MLC models can only be used for the particular label set covered in the training data. Despite this severe limitation, few methods exist for expanding the set of labels predicted by pre-trained models. Instead, we acquire vast amounts of new labeled data and retrain a new model from scratch. Here, we propose combining the knowledge from multiple pre-trained models (teachers) to train a new student model that covers the union of the labels predicted by this set of teachers. This student supports a broader label set than any one of its teachers without using labeled data. We call this new problem knowledge amalgamation for multi-label classification. Our new method, Adaptive KNowledge Transfer (ANT), trains a student by learning from each teacher’s partial knowledge of label dependencies to infer the global dependencies between all labels across the teachers. We show that ANT succeeds in unifying label dependencies among teachers, outperforming five state-of-the-art methods on eight real-world datasets.

Only a Few Classes Confusing: Pixel-Wise Candidate Labels Disambiguation for Foggy Scene Understanding

Not all semantics become confusing when deploying a semantic segmentation model for real-world scene understanding of adverse weather. The true semantics of most pixels have a high likelihood of appearing in the few top classes according to confidence ranking. In this paper, we replace the one-hot pseudo label with a candidate label set (CLS) that consists of only a few ambiguous classes and exploit its effects on self-training-based unsupervised domain adaptation. Specifically, we formulate the problem as a coarse-to-fine process. In the coarse-level process, adaptive CLS selection is proposed to pick a minimal set of confusing candidate labels based on the reliability of label predictions. Then, representation learning and label rectification are iteratively performed to facilitate feature clustering in an embedding space and to disambiguate the confusing semantics. Experimentally, our method outperforms the state-of-the-art methods on three realistic foggy benchmarks.