Label Assignment Research Articles

Compositional metric learning for multi-label classification

Multi-label classification aims to assign a set of proper labels for each instance, where distance metric learning can help improve the generalization ability of instance-based multi-label classification models. Existing multi-label metric learning techniques work by utilizing pairwise constraints to enforce that examples with similar label assignments should have close distance in the embedded feature space. In this paper, a novel distance metric learning approach for multi-label classification is proposed by modeling structural interactions between instance space and label space. On one hand, compositional distance metric is employed which adopts the representation of a weighted sum of rank-1 PSD matrices based on component bases. On the other hand, compositional weights are optimized by exploiting triplet similarity constraints derived from both instance and label spaces. Due to the compositional nature of employed distance metric, the resulting problem admits quadratic programming formulation with linear optimization complexity w.r.t. the number of training examples. We also derive the generalization bound for the proposed approach based on algorithmic robustness analysis of the compositional metric. Extensive experiments on sixteen benchmark data sets clearly validate the usefulness of compositional metric in yielding effective distance metric for multi-label classification.

Chromatic Zagreb and irregularity polynomials of graphs

Graph coloring is an assignment of colors, labels or weights to elements of a graph subject to certain constraints. Coloring the vertices of a graph in such a way that adjacent vertices are having different colors is called proper vertex coloring. A proper vertex coloring using minimum parameters of colors is studied extensively in recent literature. In this paper, we define new coloring related polynomials, called chromatic Zagreb polynomials and chromatic irregularity polynomials, in terms of minimal parameter coloring and structural characteristics of graphs such as distances and degrees of vertices.

A feature disentangling approach for person re-identification via self-supervised data augmentation

To address the problem of insufficient training data in person ReID, this paper proposes a data augmentation method based on image channels shuffling, by which a large volume of diversified training samples sharing similar edges can be produced. In the meantime, a soft label assignment strategy is designed to characterize the correlations between the original image and the generated counterparts. Furthermore, we design an encoder–decoder based learning structure for the person ReID task, where the encoder module tackles feature disentangling according to the introduced correlations, and the decoder module handles reconstruction using the combinations of decoupled features. Extensive experiments on four benchmark datasets demonstrate the effectiveness and robustness of the proposed method by attaining significant improvement over some state-of-the-art approaches. Source code is released at: https://github.com/flychen321/feature_disentangle_reid.

Unsupervised domain adaptation for person re-identification with iterative soft clustering

In this work, we propose to address the unsupervised domain adaptive (UDA) person re-id problem in which the model learns from an unlabeled target domain using a fully annotated source domain. Current approaches mainly address domain shift problem or the inter/intra-domain variation of the two domains. However, they have neglected to integrate the-easy-to-learn label distribution of the target domain into the model to improve its performance. Moreover, the automatic label assignment for the unlabeled target data currently used in UDA methods does not reflect the underlying data. To address these issues, we introduce a technique that enforces three properties: (1) target instance invariance that considers the target data and uses a key–value memory to guess the label distribution that is later used as the supervision signal. (2) a camera invariance, formed by unlabeled target images, and their camera-style transferred. Here, a new loss function is proposed to control overconfident predictions on the styled images. Lastly, (3) a hierarchical clustering-based optimization technique that exploits the similarities between the target images to constrain the supervision information of the first property. Here, we randomly allocate each target image to a separate cluster, then gradually incorporate similarity within each identity as we group similar images into clusters and use the cluster-IDs as the new target labels. We iteratively refine the guessed label distribution of the target domain by making predictions on the unlabeled target domain and then train the network with these new samples. Extensive experimental results on the concurrent use of these three properties demonstrate that the proposed model can achieve the state-of-the-art on unsupervised domain adaptive person re-id. Our work is important for knowledge discovery and knowledge transfer.

Automated cognitive health assessment in smart homes using machine learning

The Internet of Things (IoT) provides smart solutions for future urban communities to address key benefits with the least human intercession. A smart home offers the necessary capabilities to promote efficiency and sustainability to a resident with their healthcare-related, social, and emotional needs. In particular, it provides an opportunity to assess the functional health ability of the elderly or individuals with cognitive impairment in performing daily life activities. This work proposes an approach named Cognitive Assessment of Smart Home Resident (CA-SHR) to measure the ability of smart home residents in executing simple to complex activities of daily living using pre-defined scores assigned by a neuropsychologist. CA-SHR also measures the quality of tasks performed by the participants using supervised classification. Furthermore, CA-SHR provides a temporal feature analysis to estimate if the temporal features help to detect impaired individuals effectively. The goal of this study is to detect cognitively impaired individuals in their early stages. CA-SHR assess the health condition of individuals through significant features and improving the representation of dementia patients. For the classification of individuals into healthy, Mild Cognitive Impaired (MCI), and dementia categories, we use ensemble AdaBoost. This results in improving the reliability of the CA-SHR through the correct assignment of labels to the smart home resident compared with existing techniques.

Concept Factorization With Local Centroids.

Data clustering is a fundamental problem in the field of machine learning. Among the numerous clustering techniques, matrix factorization-based methods have achieved impressive performances because they are able to provide a compact and interpretable representation of the input data. However, most of the existing works assume that each class has a global centroid, which does not hold for data with complicated structures. Besides, they cannot guarantee that the sample is associated with the nearest centroid. In this work, we present a concept factorization with the local centroids (CFLCs) approach for data clustering. The proposed model has the following advantages: 1) the samples from the same class are allowed to connect with multiple local centroids such that the manifold structure is captured; 2) the pairwise relationship between the samples and centroids is modeled to produce a reasonable label assignment; and 3) the clustering problem is formulated as a bipartite graph partitioning task, and an efficient algorithm is designed for optimization. Experiments on several data sets validate the effectiveness of the CFLC model and demonstrate its superior performance over the state of the arts.

Lambda number of the power graph of a finite group

The power graph \(\Gamma _G\) of a finite group G is the graph with the vertex set G, where two distinct elements are adjacent if and only if one is a power of the other. An L(2, 1)-labeling of a graph \(\Gamma \) is an assignment of labels from nonnegative integers to all vertices of \(\Gamma \) such that vertices at distance two get different labels and adjacent vertices get labels that are at least 2 apart. The lambda number of \(\Gamma \), denoted by \(\lambda (\Gamma )\), is the minimum span or range over all L(2, 1)-labelings of \(\Gamma \). In this paper, we obtain bounds for \(\lambda (\Gamma _G)\) and give necessary and sufficient conditions when the bounds are attained. As applications, we compute the exact value of \(\lambda (\Gamma _G)\) if G is a dihedral group, a generalized quaternion group, a \({\mathcal {P}}\)-group or a cyclic group of order \(pq^n\), where p and q are distinct primes and n is a positive integer.

Weakly-supervised multi-label learning with noisy features and incomplete labels

Weakly-supervised multi-label learning has emerged as a hot topic more recently. Most existing methods deal with such problem by learning from the data where the label assignments are incomplete while the feature information is ideal. However, in many real applications, due to the influence of occlusion, illumination and low-resolution, the acquired features are often noisy, which may reduce the robustness of the learning model. In this paper, to overcome the above shortcoming, we propose a novel weakly-supervised multi-label learning framework called WML-LSC, where the low-rank and sparse constrain schemes are jointly incorporated to capture the desired feature information. Specifically, we first decompose the observed feature matrix into an ideal feature matrix and an outlier matrix. Considering that similar instances usually share similar visual characteristics, we constrain the ideal feature matrix to be low-rank. Meanwhile, a reasonable assumption is that the noise is sparse compared with the feature matrix, which leads outlier matrix to be sparse. In addition, a linear self-recovery model is adopted to reconstruct the incomplete label assignment matrix by exploiting label correlations. Finally, the desired model is trained on the ideal feature matrix and the refined label matrix. Extensive experimental results demonstrate that our proposed method can achieve superior and comparable performance against state-of-the-art methods.

Temporal structure of mouse courtship vocalizations facilitates syllable labeling

Mice emit sequences of ultrasonic vocalizations (USVs) but little is known about the rules governing their temporal order and no consensus exists on the classification of USVs into syllables. To address these questions, we recorded USVs during male-female courtship and found a significant temporal structure. We labeled USVs using three popular algorithms and found that there was no one-to-one relationships between their labels. As label assignment affects the high order temporal structure, we developed the Syntax Information Score (based on information theory) to rank labeling algorithms based on how well they predict the next syllable in a sequence. Finally, we derived a novel algorithm (Syntax Information Maximization) that utilizes sequence statistics to improve the clustering of individual USVs with respect to the underlying sequence structure. Improvement in USV classification is crucial for understanding neural control of vocalization. We demonstrate that USV syntax holds valuable information towards achieving this goal.

Weak Disambiguation for Partial Structured Output Learning.

Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n -slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model.

Towards multi-center glaucoma OCT image screening with semi-supervised joint structure and function multi-task learning.

Glaucoma is the leading cause of irreversible blindness in the world. Structure and function assessments play an important role in diagnosing glaucoma. Nowadays, Optical Coherence Tomography (OCT) imaging gains increasing popularity in measuring the structural change of eyes. However, few automated methods have been developed based on OCT images to screen glaucoma. In this paper, we are the first to unify the structure analysis and function regression to distinguish glaucoma patients from normal controls effectively. Specifically, our method works in two steps: a semi-supervised learning strategy with smoothness assumption is first applied for the surrogate assignment of missing function regression labels. Subsequently, the proposed multi-task learning network is capable of exploring the structure and function relationship between the OCT image and visual field measurement simultaneously, which contributes to classification performance improvement. It is also worth noting that the proposed method is assessed by two large-scale multi-center datasets. In other words, we first build the largest glaucoma OCT image dataset (i.e., HK dataset) involving 975,400 B-scans from 4,877 volumes to develop and evaluate the proposed method, then the model without further fine-tuning is directly applied on another independent dataset (i.e., Stanford dataset) containing 246,200 B-scans from 1,231 volumes. Extensive experiments are conducted to assess the contribution of each component within our framework. The proposed method outperforms the baseline methods and two glaucoma experts by a large margin, achieving volume-level Area Under ROC Curve (AUC) of 0.977 on HK dataset and 0.933 on Stanford dataset, respectively. The experimental results indicate the great potential of the proposed approach for the automated diagnosis system.

A game-based framework for crowdsourced data labeling

Data labeling, which assigns data with multiple classes, is indispensable for many applications, such as machine learning and data integration. However, existing labeling solutions either incur expensive cost for large datasets or produce noisy results. This paper introduces a cost-effective labeling approach and focuses on the labeling rule generation problem that aims to generate high-quality rules to largely reduce the labeling cost while preserving quality. To address the problem, we first generate candidate rules and then devise a game-based crowdsourcing approach CrowdGame to select high-quality rules by considering coverage and accuracy. CrowdGame employs two groups of crowd workers: One group answers rule validation tasks (whether a rule is valid) to play a role of rule generator, while the other group answers tuple checking tasks (whether the label of a data tuple is correct) to play a role of rule refuter. We let the two groups play a two-player game: Rule generator identifies high-quality rules with large coverage, while rule refuter tries to refute its opponent rule generator by checking some tuples that provide enough evidence to reject rules with low accuracy. This paper studies the challenges in CrowdGame. The first is to balance the trade-off between coverage and accuracy. We define the loss of a rule by considering the two factors. The second is rule accuracy estimation. We utilize Bayesian estimation to combine both rule validation and tuple checking tasks. The third is to select crowdsourcing tasks to fulfill the game-based framework for minimizing the loss. We introduce a minimax strategy and develop efficient task selection algorithms. We also develop a hybrid crowd-machine method for effective label assignment under budget-constrained crowdsourcing settings. We conduct experiments on entity matching and relation extraction, and the results show that our method outperforms state-of-the-art solutions.

Robust TSK Fuzzy System Based on Semisupervised Learning for Label Noise Data

As an important branch in the field of soft computing, TSK fuzzy systems have been diversely applied to supervised learning in recent years. However, real-world data may contain label noise, which has a negative impact on supervised learning. Label noise samples change the distribution of samples in each class, mislead learning algorithms and make classification problems more complicated. There are various sources of label noise, such as wrong assignment of labels during the data collection, contamination during the data storage, and so on. Thus, it is usually costly and time-consuming to obtain data with no label noise. When dealing with label noise data, existing TSK fuzzy system algorithms still have room for improvement. This article proposes a robust TSK fuzzy system based on semisupervised learning for label noise data (RTSK-FS-SS). By introducing an intuitionistic fuzzy set method, the proposed algorithm can detect label noise samples. An improved learning vector quantization is further adopted to overcome the challenge that traditional unsupervised learning-based antecedent part generation processes unable to make full use of the label information of training samples. Finally, we discard the label of suspicious samples and a consequent parameter learning method based on semisupervised learning is proposed. The proposed algorithm is validated using extensive experiments.

Sparse neighbor constrained co-clustering via category consistency learning

Clustering has long been an enduring and promising task in machine learning. However, developed one-side clustering is still insufficient to explore the context of data, such as texts and genes. Hence, developing two-way clustering has drawn more attention in recent years, which tends to cluster samples and features simultaneously. This paper proposes a sparse neighbor constrained co-clustering via category consistency learning, for alleviating the misclassification of close points. Following an additional observation, samples often fall into the same category as their neighbors, as do features. Accordingly, the co-clustering problem is formulated as nonnegative matrix tri-factorization appended dual regularizers, considering coherence between data affinity and label assignment. Then, a multiplicative alternating scheme is raised for objective optimization, whose convergence and correctness are theoretically guaranteed. Furthermore, the proposed approach is validated on six datasets using three evaluation metrics, whose parameter sensitivity is analyzed as well. Finally, comprehensive experiments show that our algorithm is competitive against existing ones.

Visual BMI estimation from face images using a label distribution based method

Body mass index (BMI) analysis from face images is an interesting and challenging topic in machine learning and computer vision. Recent research shows that facial adiposity is associated with BMI prediction. In this work, we investigate the problem of visual BMI estimation from face images by a two-stage learning framework. BMI-related facial features are learned from the first stage. Then a label distribution based BMI estimator is learned by an optimization procedure that is implemented by projecting the features and assigned labels to a new domain which maximizing the correlation between them. Two label assignment strategies are analyzed for modeling the single BMI value as a discrete probability distribution over a range of BMIs. Extensive experiments are conducted on FIW-BMI, Morph II and VIP_attribute datasets. The experimental results show that the two-stage learning framework improves the performance step by step. More importantly, the proposed BMI estimator efficiently reduces the error. It outperforms regression based methods, two label distribution methods and two deep learning methods in most cases.

A comprehensive survey on 3-equitable and divisor 3-equitable labeling of graphs

This article presents a short survey on 3-equitable and divisor 3-equitable labeling of graphs. For any graph G(V,E) and k > 0, assign vertex labels from {0,1,…, k − 1} such that when the edge labels induced by the absolute value of the difference of the vertex labels, the number of vertices labeled with i and the number of vertices labeled with j differ by at most one and the number of edges labeled with i and the number of edges labeled with j differ by at most one. We call a graph G with such an assignment of labels k –equitable. When k = 3, it becomes a 3-equitable labeling. In 2019, Sweta Srivastav et al. introduced the notion of divisor 3-equitable labeling of graphs. A bijection f: V(G) → {1, 2, …,n} induces a function f':E(G) → {0,1,2} defined by for each edge e = xy, (i) f'(e) = 1 if f(x)|f(y) or f(y)|f(x), (ii) f'(e) = 2 if f(x)/f(y) = 2 or f(y)/f(x) = 2, and (iii) f'(e) = 0 otherwise such that for all 0 ≤ i,j ≤ 2. A graph which admits a divisor 3-equitable labeling is called a divisor 3-equitable graph. This article stands divided into five sections. The first and fifth sections are reserved respectively for introduction and some important references. The second section deals with the 3-equitable labeling of graphs wherein some important known results have been recalled. The third section deals with the divisor 3-equitable labeling of graphs wherein a few known results have been outlined. In the fourth section we highlight certain conjectures and open problems in respect of the above mentioned labeling that still remain unsolved.

Divisor Labeling of Some Special Graphs

An assignment of labels (mostly, integers) to the vertices of a graph G(V,E), or simply G, on n vertices subject to certain constraints is called a vertex labeling of G. A graph G is a divisor graph if the vertices of G can be labeled with integers (necessarily distinct) in such a way that either x|y or y|x for any two adjacent vertices x and y. In this paper, we encounter the divisor labeling of certain classes of graphs.

EHANet: An Effective Hierarchical Aggregation Network for Face Parsing

In recent years, benefiting from deep convolutional neural networks (DCNNs), face parsing has developed rapidly. However, it still has the following problems: (1) Existing state-of-the-art frameworks usually do not satisfy real-time while pursuing performance; (2) similar appearances cause incorrect pixel label assignments, especially in the boundary; (3) to promote multi-scale prediction, deep features and shallow features are used for fusion without considering the semantic gap between them. To overcome these drawbacks, we propose an effective and efficient hierarchical aggregation network called EHANet for fast and accurate face parsing. More specifically, we first propose a stage contextual attention mechanism (SCAM), which uses higher-level contextual information to re-encode the channel according to its importance. Secondly, a semantic gap compensation block (SGCB) is presented to ensure the effective aggregation of hierarchical information. Thirdly, the advantages of weighted boundary-aware loss effectively make up for the ambiguity of boundary semantics. Without any bells and whistles, combined with a lightweight backbone, we achieve outstanding results on both CelebAMask-HQ (78.19% mIoU) and Helen datasets (90.7% F1-score). Furthermore, our model can achieve 55 FPS on a single GTX 1080Ti card with 640 × 640 input and further reach over 300 FPS with a resolution of 256 × 256, which is suitable for real-world applications.

Tree-Antimagicness of Web Graphs and Their Disjoint Union

In graph theory, the graph labeling is the assignment of labels (represented by integers) to edges and/or vertices of a graph. For a graph G=V,E, with vertex set V and edge set E, a function from V to a set of labels is called a vertex labeling of a graph, and the graph with such a function defined is called a vertex-labeled graph. Similarly, an edge labeling is a function of E to a set of labels, and in this case, the graph is called an edge-labeled graph. In this research article, we focused on studying super ad,d-T4,2-antimagic labeling of web graphs W2,n and isomorphic copies of their disjoint union.

Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification

Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called Viewpoint-Aware Loss with Angular Regularization (VA-reID). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.