Identity Labels Research Articles

Information filtering and interpolating for semi-supervised graph domain adaptation

Graph domain adaptation, which falls under the umbrella of graph transfer learning, involves transferring knowledge from a labeled source graph to improve prediction accuracy on an unlabeled target graph, where both graphs have identical label spaces but exhibit distribution discrepancies due to temporal data shifts or distinct data collection methods. This adaptation is complicated by the challenges of graph-specific domain discrepancies and cross-graph label scarcity. This paper proposes a semi-supervised Graph domain adaptation method via Information Filtering and Interpolating (GIFI). Specifically, GIFI utilizes a parameterized graph reduction module and a variational information bottleneck to adequately filter out irrelevant information from the source and target graphs to eliminate distribution discrepancy. GIFI also introduces an interpolation-enhanced pseudo-labeling strategy for cross-graph semi-supervised learning, which can mitigate model over-fitting on domain-specific features and limited labeled nodes, thus improving the model’s adaptation and discriminative capability. Experimental results on various graph domain adaptation benchmarks demonstrate GIFI’s superior performance over state-of-the-art methods. Our code is available at https://github.com/joe817/GIFI.

Challenging the local logics of oppression in times of post-colonial amnesia – a study of Ugandan LGBT+ activism in digital media spaces

ABSTRACT Against the backdrop of an increasingly repressive environment, the study explores to what degree five established LGBT+ organizations use self-controlled digital spaces, Twitter and Facebook, during one month in 2022 to expose and challenge constructs that rationalize oppression of Ugandan LGBT+. The analysis revealed that digital media spaces were not used to challenge the local logics of oppression or contemporary processes sustaining oppression. Instead, spaces, often displaying a conspicuously uniform Western sexual rights language, focused on providing digital services and/or notification of offline services to the community and promoting the individual organization. The adoption of Western sexual rights campaign language, including using LGBT+ as identity labels to communicate Ugandan same-sex desires and gender identities, could be explained by the community’s dependency on international resources. The study’s contribution lies in its astute reminder – that the realization of digital spaces’ emancipatory potential is dependent on the political economy of the activists' context.

The Role of Feminism and Gender in Endorsement of Hookup Culture among Emerging Adults.

Hookup culture has transformed the sexual behavior of emerging adults. Feminism, a movement that has advocated for liberating women from sexual repression, may be associated with hookup endorsement attitudes. This study explores the associations among multiple dimensions of feminism, gender, and hookup culture endorsement. Participants included 318 emerging adults (46% women; Mage = 22.2 years; 51% White, 27% Asian, 5% Hispanic/Latinx, 9% Black, 1% Middle Eastern, 1% American Indian, 6% Multiracial) from five Anglophone countries (62% U.S., 23% United Kingdom, 9% Canada, 5% Australia, 1% New Zealand), who completed the Feminist Beliefs and Behavior Scale and Endorsement of Hookup Culture Index via an anonymous, online survey. Participants were categorized according to their feminist identity label (feminist, non-feminist) and feminist belief system (hold feminist beliefs, hold non-feminist beliefs). A series of ANCOVAs was conducted, revealing that women who identified as feminist and/or held feminist beliefs reported significantly higher endorsement of hookup culture compared to non-feminist women with non-feminist beliefs. Neither dimension of feminism predicted hookup culture endorsement in men. When comparing feminist-identifying women and men, the gender disparity in hookup culture endorsement was eliminated. Together, these findings highlight how social movements, such as feminism, may be associated with young women's attitudes towards hookups, and may ultimately shape their sexual experiences.

What’s in a Label? Public Use and Perceptions of Labeling Alternatives in Criminology

Research indicates that crime-first language (“criminal”) increases stigma, but there is limited evidence comparing person-first language (“person with a conviction”) to other non-deviant terminology. Using two survey experiments, we test whether using person-first language in the employment context has a mimicry effect (i.e. people adopt language they are exposed to) and whether language has a stronger influence when paired with positive employment credentials. We do not find consistent evidence of mimicry. Respondents viewing a positive credential were more likely to use person-centered or professional language and positive credentials generally improved perceptions of the applicant. However, person-first language can cancel out beneficial credential effects compared to alternative language. When considering alternatives to crime-first language, two implications emerge: positive information is more consistently influential than the terminology used, and after establishing a person has a criminal record, substituting other identity labels (e.g. person, applicant) can further reduce stigma.

MP2PMatch: A Mask-guided Part-to-Part Matching network based on transformer for occluded person re-identification

Occluded person re-identification (ReID) remains challenging due to the misaligned body parts. Existing works, mainly utilizing extra clues, excel in predicting holistic person images but falter when confronting substantial occlusion. This paper proposes a transformer-based Mask-guided Part-to-Part Matching (MP2PMatch) network for fine-grained matching. Firstly, the Consistency Occlusion Augmentation (COA) processes holistic person images and corresponding body part masks to construct occluded “image-mask” pairs. Next, we introduce learnable part tokens to capture semantic features of various body parts, performing “pull close” and “push apart” operations based on identity labels and part visibility, ensuring the one-to-one correspondence between part features and body parts. Additionally, the proposed Body Region Attention (BRA) utilizes the overall attention on body regions to guide the network to overcome interference from both occlusion and background. Extensive experiments demonstrate that MP2PMatch achieves exceptional occluded ReID performance.

A dual-weighted adversarial network for partial domain fault diagnosis of machinery

Domain adaptation provides a promising approach to cross-domain fault diagnosis of rotating machinery. While many current methods focus on scenarios where the source and target domains share identical label spaces, a prevalent situation in industrial production involves the target domain being a subset of the source domain, known as partial domain adaptation (PDA). The main challenge in PDA is the label mismatches caused by outlier classes, making the alignment between domains particularly difficult. To this end, a dual-weighted adversarial network is proposed in this paper. Specifically, a bilateral class weighting strategy (BCWS) is developed, which can effectively suppress negative migration at the decision boundary while improving the robustness of adversarial training by applying bilateral weighting to both the source and target domains. Moreover, a collaborative framework is developed to facilitate positive migration. The constructed global perceptual module (GPM) is highly correlated with the improved adversarial loss function, which adaptively adjusts the input feature map according to the accuracy of the target domain classification and pays more attention to the domain-invariant features. Experimental results for two cases, namely across different operating conditions and across different rotating components, verify the effectiveness and superiority of the proposed method for the PDA problem.

GaitSCM: Causal representation learning for gait recognition

Gait recognition is a promising biometric technology that aims to identify the target subject via walking pattern. Most existing appearance-based methods focus on learning discriminative spatio-temporal representations from gait silhouettes. However, these methods pay less attention to probing the causality between identity factors and identity labels, which often mislead the model to learn gait representations that are susceptible to identity-irrelevant factors. In this paper, we attribute the cause that leads to the decline of model generalization under different external conditions to identity-irrelevant factors. We formulate the causalities among the identity factors, identity-irrelevant factors, and identity labels as a structural causal model (SCM). We accordingly propose a novel gait recognition framework named GaitSCM to learn covariate invariant gait representations, which is mainly composed of three components, including feature extraction module, feature disentanglement module, and backdoor adjustment. Specifically, we design a feature extractor with regard to the movement patterns of different body parts to learn fine-grained gait motion features, and then present a two-branch feature decoupling module to disentangle identity features and identity-irrelevant features with the aid of the classification confusion loss. To relieve the negative effect of identity-irrelevant factors, we develop a backdoor adjustment strategy to eliminate spurious associations between identity and identity-irrelevant features, which further facilitates the proposed framework to generate more powerful identity representations. Extensive experiments conducted on two public datasets validate the effectiveness of our method. The average Rank-1 can reach 93.2% and 90.4% on CASIA-B and OU-MVLP datasets, respectively, which verifies the superiority of GaitSCM. Source code is released at: https://github.com/HuoweiCode/GaitSCM.

Pagans on campus: A cursory exploration

AbstractPaganism, despite growing as a religious affiliation over recent decades, has rarely been the subject of study within higher education. Due to the general lack of cohesive organizations, a persistent social stigma, and a number of ill‐defined identity labels, they have proven difficult to study even within the general population. This chapter will provide a descriptive snapshot of the population of Pagan college students in the United States and offer guidance for higher education practitioners working with this often‐invisible religious demographic group on their campuses.Practical Takeaways Pagans remain a small population, which can be an isolating experience for students, particularly given their tendency for solitary practice. Even for Pagan students who want to practice in a community, their small numbers—as well as their social stigma—can make organization difficult. For these and other reasons, social isolation is a pressing concern for Pagan students. Demographically, Pagan students appear to identify as LGB and with gender identities outside of the binary norm at higher rates than the general population of college students. Expressions of these identities may be sources of tension with other religious groups on campus, as well as with individual student peers. Campus professionals should note this tendency when considering the power dynamics at play in their campus spaces. Spiritual customs for Pagans are often personal, personalized, and frequently private. The holidays, practices, and symbols may be strange or even alarming to outsider peers and campus professionals, so it is not unusual for Pagans to conceal them.

Art worlds in light of identity labeling

Art worlds in light of identity labeling

Fluidity in Reporting Gender Identity Labels in a Sample of Transgender and Gender Diverse Adolescents and Young Adults, Los Angeles, California, and New Orleans, Louisiana, 2017-2019.

Treating gender identity as a fixed characteristic may contribute to considerable misclassification and hinder accurate characterization of health inequities and the design of effective preventive interventions for transgender and gender diverse (TGD) adolescents and young adults. We examined changes in how an ethnically and racially diverse sample of TGD adolescents and young adults reported their gender identity over time, the implications of this fluidity on public health, and the potential effects of misclassification of gender identity. We recruited 235 TGD adolescents and young adults (aged 15-24 y) in Los Angeles, California, and New Orleans, Louisiana, from May 2017 through August 2019 to participate in an HIV intervention study. We asked participants to self-report their gender identity and sex assigned at birth every 4 months for 24 months. We used a quantitative content analysis framework to catalog changes in responses over time and classified the changes into 3 main patterns: consistent, fluctuating, and moving in 1 direction. We then calculated the distribution of gender identity labels at baseline (initial assessment) and 12 and 24 months and described the overall sample by age, race, ethnicity, and study site. Of 235 TGD participants, 162 (69%) were from Los Angeles, 89 (38%) were Latinx, and 80 (34%) were non-Latinx Black or African American. Changes in self-reported gender identity were common (n = 181; 77%); in fact, 39 (17%) changed gender identities more than twice. More than 50% (n = 131; 56%) showed a fluctuating pattern. Gender identity labels varied over time, suggesting that misclassification may occur if data from a single time point are used to define gender identity. Our study lays the foundation for launching studies to elucidate the associations between shifting gender identities and health outcomes.

Weakly Supervised Contrastive Learning for Unsupervised Vehicle Reidentification.

Reidentification (Re-id) of vehicles in a multicamera system is an essential process for traffic control automation. Previously, there have been efforts to reidentify vehicles based on shots of images with identity (id) labels, where the model training relies on the quality and quantity of the labels. However, labeling vehicle ids is a labor-intensive procedure. Instead of relying on expensive labels, we propose to exploit camera and tracklet ids that are automatically obtainable during a Re-id dataset construction. In this article, we present weakly supervised contrastive learning (WSCL) and domain adaptation (DA) techniques using camera and tracklet ids for unsupervised vehicle Re-id. We define each camera id as a subdomain and tracklet id as a label of a vehicle within each subdomain, i.e., weak label in the Re-id scenario. Within each subdomain, contrastive learning using tracklet ids is applied to learn a representation of vehicles. Then, DA is performed to match vehicle ids across the subdomains. We demonstrate the effectiveness of our method for unsupervised vehicle Re-id using various benchmarks. Experimental results show that the proposed method outperforms the recent state-of-the-art unsupervised Re-id methods. The source code is publicly available on https://github.com/andreYoo/WSCL_VeReid.

Analysis of Material Unavailability in the Beside Table Production Process Using Root Cause Analysis (RCA) and 5SMethods in A Furniture Company

Furniture manufacturing company, producing products such as tenban, beside cabinet, beside table. In carrying out its production, furniture companies often occur conditions of material unavailability when the production process is in progress and there is a difference between the amount of material inventory stock in the information system (computer) and the stock of materials in the warehouse. This research will identify the factors that cause material unavailability during production using the Root cause analysis (RCA) method. Several factors causematerial unavailability, namely, errors in inputting material stock data, not doing physical stock-taking regularly, material moving to other parts of the shelf, material storage is not neat because there are few storage shelves and material identity labels are not yet valid, recording stock-taking is still manual, material or spare parts are lost, return material (defects) from users is placed on the same shelf as OK material and narrow warehouse space and limited storage shelves. To overcome these problems, this research provides a sustainable improvement proposal by implementing the lean thinking concept with the 5S principle in the company. It is expected that with the application of the 5S concept in this company so that the material inventory system in the warehouse is controlled optimally so that it can increase the productivity of employee performance in the company and a better change for the company.

Pseudo Label Association and Prototype-Based Invariant Learning for Semi-Supervised NIR-VIS Face Recognition.

Remarkable success of the existing Near-InfraRed and VISible (NIR-VIS) approaches owes to sufficient labeled training data. However, collecting and tagging data from different domains is a time-consuming and expensive task. In this paper, we tackle the NIR-VIS face recognition problem in a semi-supervised manner, termed as semi-supervised NIR-VIS Heterogeneous Face Recognition (NIR-VIS-sHFR). To cope with this problem, we propose a novel pseudo Label association and Prototype-based invariant Learning (LPL), consisting of three key components, i.e., Cross-domain pseudo Label Association (CLA), Intra-domain Compact Representation learning (ICR), and Prototype-based Inter-domain Invariant learning (PII). Firstly, the CLA iteratively builds inter-domain association graphs for pseudo-label association, subsequently facilitating cross-domain model development based on the generated pseudo-labels. Furthermore, the ICR is proposed to achieve the separation of in-domain features from different clusters and the aggregation of features from the same cluster, by performing cluster adaptation learning with prototype-based initialization. Finally, with the cross-domain pseudo-label training data produced by CLA, the PII explores potential domain-invariant and identity-related features, which employs cross-domain prototypes with identity-associated momentum updating to effectively guide inter-domain instances learning. The semi-supervised LPL method achieves comparable performance to recent supervised learning methods on multiple challenging NIR-VIS datasets, which demonstrates that the LPL is capable of learning robust cross-domain representations even without identity label information.

Relation-Preserving Feature Embedding for Unsupervised Person Re-Identification

Some unsupervised approaches have been proposed recently for the person re-identification (ReID) problem since annotations of samples across cameras are time-consuming. However, most of these methods focus on the appearance content of the sample itself, and thus seldom take the structure relations among samples into account when learning the feature representation, which would provide a valuable guide for learning the representations of the samples. Thus hard samples may not be well solved due to the limited or even misleading information of the sample itself. To address this issue, in this paper, we propose a Relation-Preserving Feature Embedding (RPE) model that leverages structure relations among samples to boost the performance of the unsupervised person ReID methods without requiring any sample annotations. RPE aims at integrating the sample content and the neighborhood structure relations among samples into the learning of feature embeddings by combining the advantages of the autoencoder and graph autoencoder. Specifically, a relation and content information fusion (RCIF) module is proposed to dynamically merge the information from both perspectives of content and relation levels for feature embedding learning. Also, due to the lack of the identity labels of samples, we adopt an adaptive optimization strategy to update the affinity relations among samples instead of the reconstruction of the whole affinity matrix for optimizing the RPE model, which is more suitable for the unsupervised ReID task. Rigorous experiments on three widely-used large-scale benchmarks for person ReID demonstrate the superiority of the proposed method over current state-of-the-art unsupervised methods.

Detection of common subtrees with identical label distribution

Frequent pattern mining is a relevant method to analyse structured data, like sequences, trees or graphs. It consists in identifying characteristic substructures of a dataset. This paper deals with a new type of patterns for tree data: common subtrees with identical label distribution. Their detection is far from obvious since the underlying isomorphism problem is graph isomorphism complete. An elaborated search algorithm is developed and analysed from both theoretical and numerical perspectives. Based on this, the enumeration of patterns is performed through a new lossless compression scheme for trees, called DAG-RW, whose complexity is investigated as well. The method shows very good properties, both in terms of computation times and analysis of real datasets from the literature. Compared to other substructures like topological subtrees and labelled subtrees for which the isomorphism problem is linear, the patterns found provide a more parsimonious representation of the data.

Differences in Minority Stress Experiences, Mental Health, and Relationship Quality Outcomes Among Bisexual, Pansexual, and Queer Women.

The majority of sexual minority women in the United States today identify as bi+. Recent research suggests that "non-traditional" bi+ labels such as pansexual and queer are being adopted more frequently than ever before, making it increasingly important to evaluate whether these women have unique needs. In the current study, we explored differences in minority stress experiences, mental health, and relationship quality outcomes by sexual identity label among women who identify with the most common bi+ labels: bisexual, pansexual, and queer. Participants were 285 bi+ cisgender women in romantic relationships. They completed online measures of minority stress (antibisexual experiences, identity concealment, disconnection from the sexual and gender minority (SGM) community, and internalized stigma), mental health (depression and anxiety), and relationship quality (satisfaction and commitment). Overall, participants reported similar experiences of minority stress and few differences in their mental health outcomes. However, there were differences in antibisexual experiences by sexual identity label, such that pansexual women reported more frequent antibisexual experiences than bisexual and queer women. There were also differences in relationship quality by sexual identity label, such that bisexual women reported higher satisfaction than pansexual women and higher commitment than both pansexual and queer women. Findings suggest that pansexual and queer women may be facing their own unique challenges, even compared to bisexual women. Clinical prevention and intervention efforts can be tailored for these women to include strategies to cope with more frequent exposure to antibisexual experiences, as well as relationship education and skill-building to promote healthy romantic relationships.

Classifying real-world macroscopic images in the primary-secondary care interface using transfer learning: implications for development of artificial intelligence solutions using nondermoscopic images.

The application of deep learning (DL) to diagnostic dermatology has been the subject of numerous studies, with some reporting skin lesion classification performance on curated datasets comparable to that of experienced dermatologists. Most skin disease images encountered in clinical settings are macroscopic, without dermoscopic information, and exhibit considerable variability. Further research is necessary to determine the generalizability of DL algorithms across populations and acquisition settings. To assess the extent to which DL can generalize to nondermoscopic datasets acquired at the primary-secondary care interface in the National Health Service (NHS); to explore how to obtain a clinically satisfactory performance on nonstandardized, real-world local data without the availability of large diagnostically labelled local datasets; and to measure the impact of pretraining DL algorithms on external, public datasets. Diagnostic macroscopic image datasets were created from previous referrals from primary to secondary care. These included 2213 images referred from primary care practitioners in NHS Tayside and 1510 images from NHS Forth Valley acquired by medical photographers. Two further datasets with identical diagnostic labels were obtained from sources in the public domain, namely the International Skin Imaging Collaboration (ISIC) dermoscopic dataset and the SD-260 nondermoscopic dataset. DL algorithms, specifically EfficientNets and Self-attention with Window-wise Inner-product based Network (SWIN) transformers, were trained using data from each of these datasets. Algorithms were also fine-tuned on images from the NHS datasets after pretraining on different data combinations, including the larger public-domain datasets. Receiver operating characteristic curves and the area under such curves (AUC) were used to assess performance. SWIN transformers tested on Forth Valley data had AUCs of 0.85 and 0.89 when trained on SD-260 and Forth Valley data, respectively. Training on SD-260 followed by fine tuning of Forth Valley data gave an AUC of 0.91. Similar effects of pretraining and tuning on local data were observed using Tayside data and EfficientNets. Pretraining on the larger dermoscopic image dataset (ISIC 2019) provided no additional benefit. Pretraining on public macroscopic images followed by tuning to local data gave promising results. Further improvements are needed to afford deployment in real clinical pathways. Larger datasets local to the target domain might be expected to yield further improved performance.

Novel adaptive loss weighted transfer network for partial domain fault diagnosis

Mechanical fault transfer diagnosis has been confirmed as a feasible approach for tackling intelligent diagnosis with incomplete fault information and scarce labeled data on the basis of big data through the transfer of diagnostic knowledge from one or more conditions to any other condition. However, existing research has developed a hypothesis, i.e., the target domain shares an identical label space with the source domain, making it unfeasible to address the practical issue that the target domain label space is a subset of the source domain label space, resulting in low transfer diagnosis accuracy. To address this issue, a novel unsupervised intelligent diagnosis approach named double classifiers-dependent transfer diagnosis network is developed. In this approach, the label distribution weights are generated through the probability output of the classifier of source domain label space to target domain samples, by which small weights are assigned to irrelevant source samples to avoid negative transfer in the global-local maximum mean discrepancies (GL-MMD). In addition, classifiers of the source domain label space and the shared label space are built separately to improve the reliability of label distribution weights and GL-MMD. By training the network in the shared label space, diagnostic knowledge in partial domain issues is effectively transferred. Two cases are implemented to verify the effectiveness of the developed approach. Compared with other transfer diagnosis approaches, the developed approach achieved better diagnostic performance.

Learning Semantics-Consistent Stripes With Self-Refinement for Person Re-Identification.

Aligning human parts automatically is one of the most challenging problems for person re-identification (re-ID). Recently, the stripe-based methods, which equally partition the person images into the fixed stripes for aligned representation learning, have achieved great success. However, the stripes with fixed height and position cannot well handle the misalignment problems caused by inaccurate detection and occlusion and may introduce much background noise. In this article, we aim at learning adaptive stripes with foreground refinement to achieve pixel-level part alignment by only using person identity labels for person re-ID and make two contributions. 1) A semantics-consistent stripe learning method (SCS). Given an image, SCS partitions it into adaptive horizontal stripes and each stripe is corresponding to a specific semantic part. Specifically, SCS iterates between two processes: i) clustering the rows to human parts or background to generate the pseudo-part labels of rows and ii) learning a row classifier to partition a person image, which is supervised by the latest pseudo-labels. This iterative scheme guarantees the accuracy of the learned image partition. 2) A self-refinement method (SCS+) to remove the background noise in stripes. We employ the above row classifier to generate the probabilities of pixels belonging to human parts (foreground) or background, which is called the class activation map (CAM). Only the most confident areas from the CAM are assigned with foreground/background labels to guide the human part refinement. Finally, by intersecting the semantics-consistent stripes with the foreground areas, SCS+ locates the human parts at pixel-level, obtaining a more robust part-aligned representation. Extensive experiments validate that SCS+ sets the new state-of-the-art performance on three widely used datasets including Market-1501, DukeMTMC-reID, and CUHK03-NP.

Multi target tracking algorithm based on anchor free detection

In order to alleviate the problems of frequent identity label switching caused by mutual occlusion between targets and missed detection caused by small target sizes in multi-target tracking, this paper proposes a multi-target tracking algorithm based on anchor-free detection. This algorithm first uses YOLOX for detection and embeds the ReID algorithm to enhance pedestrian recognition. Then, it uses the DeepSORT algorithm for tracking and correcting abnormal trajectory algorithms for occluded targets. Finally, experiments are conducted on both the MOT16 dataset and the self-made dataset. This algorithm has higher tracking accuracy than other algorithms, and its tracking performance for small targets has also been effectively improved.