Style Diversity Research Articles

Style Variable and Irrelevant Learning for Generalizable Person Re-identification

Domain generalization person re-identification (DG-ReID) has gained much attention recently due to the poor performance of supervised re-identification on unseen domains. The goal of domain generalization is to develop a model that is insensitive to domain bias and can perform well across different domains. In this article, We conduct experiments to verify the importance of style factors in domain bias. Specifically, the experiments are to affirm that style bias across different domains significantly contributes to domain bias. Based on this observation, we propose style variable and irrelevant learning (SVIL) to eliminate the influence of style factors on the model. Specifically, we employ a style jitter module (SJM) that enhances the style diversity of a specific source domain and reduces the style differences among various source domains. This allows the model to focus on identity-relevant information and be robust to style changes. We also integrate the SJM module with a meta-learning algorithm to further enhance the model’s generalization ability. Notably, our SJM module is easy to implement and does not add any inference cost. Our extensive experiments demonstrate the effectiveness of our approach, which outperforms existing methods on DG-ReID benchmarks.

Domain adaptive noise reduction with iterative knowledge transfer and style generalization learning

Low-dose computed tomography (LDCT) denoising tasks face significant challenges in practical imaging scenarios. Supervised methods encounter difficulties in real-world scenarios as there are no paired data for training. Moreover, when applied to datasets with varying noise patterns, these methods may experience decreased performance owing to the domain gap. Conversely, unsupervised methods do not require paired data and can be directly trained on real-world data. However, they often exhibit inferior performance compared to supervised methods. To address this issue, it is necessary to leverage the strengths of these supervised and unsupervised methods. In this paper, we propose a novel domain adaptive noise reduction framework (DANRF), which integrates both knowledge transfer and style generalization learning to effectively tackle the domain gap problem. Specifically, an iterative knowledge transfer method with knowledge distillation is selected to train the target model using unlabeled target data and a pre-trained source model trained with paired simulation data. Meanwhile, we introduce the mean teacher mechanism to update the source model, enabling it to adapt to the target domain. Furthermore, an iterative style generalization learning process is also designed to enrich the style diversity of the training dataset. We evaluate the performance of our approach through experiments conducted on multi-source datasets. The results demonstrate the feasibility and effectiveness of our proposed DANRF model in multi-source LDCT image processing tasks. Given its hybrid nature, which combines the advantages of supervised and unsupervised learning, and its ability to bridge domain gaps, our approach is well-suited for improving practical low-dose CT imaging in clinical settings. Code for our proposed approach is publicly available at https://github.com/tyfeiii/DANRF.

The effect of novel linguistic-based review features on review helpfulness through information ecosystem and ELM theories: Heterogeneity analysis across platforms

Although online review helpfulness has been extensively discussed, examining it at the platform level can still yield new insights. Drawing on ELM and information ecosystem theories, this study identifies heterogeneity in review features and their impact on helpfulness across platforms through a multimethod analysis of 82,130 reviews on JD and TikTok. Econometric analysis revealed that reviews on mature platforms contain richer objective content, more diverse language styles, and stronger semantic associations. In terms of content, objective content diversity positively affects helpfulness on emerging platforms, while it has the opposite effect on mature platforms. Negative sentiment significantly affects helpfulness only on mature platforms, and positive sentiment has no significant effect on either platform. In terms of language style, the analysis indicated that language style diversity positively impacts the helpfulness of emerging platforms. However, four specific styles (figurative, comparative, interrogative and exaggerative) negatively affect helpfulness on emerging platforms, with only comparative style having a significant negative effect on mature platforms. In terms of semantic association, the results show a more substantial positive impact on emerging platforms. Machine learning-based performance analysis corroborates the core findings of the econometric analysis. This study provides novel findings to the existing literature and provides managerial implications for different platforms.

Class conditioned text generation with style attention mechanism for embracing diversity

In the field of artificial intelligence and natural language processing (NLP), natural language generation (NLG) has significantly advanced. Its primary aim is to automatically generate text in a manner resembling human language. Traditional text generation has mainly focused on binary style transfers, limiting the scope to simple transformations between positive and negative tones or between modern and ancient styles. However, accommodating style diversity in real scenarios presents greater complexity and demand. Existing methods usually fail to capture the richness of diverse styles, hindering their utility in practical applications. To address these limitations, we propose a multi-class conditioned text generation model. We overcome previous constraints by utilizing a transformer-based decoder equipped with adversarial networks and style-attention mechanisms to model various styles in multi-class text. According to our experimental results, the proposed model achieved better performance compared to the alternatives on multi-class text generation tasks in terms of diversity while it preserves fluency. We expect that our study will help researchers not only train their models but also build simulated multi-class text datasets for further research.

Polyp Generalization via Diversifying Style at Feature-Level Space

In polyp segmentation, the latest notable topic revolves around polyp generalization, which aims to develop deep learning-based models capable of learning from single or multiple source domains and applying this knowledge to unseen datasets. A significant challenge in real-world clinical settings is the suboptimal performance of generalized models due to domain shift. Convolutional neural networks (CNNs) are often biased towards low-level features, such as style features, impacting generalization. Despite attempts to mitigate this bias using data augmentation techniques, learning model-agnostic and class-specific feature representations remains complex. Previous methods have employed image-level transformations with styles to supplement training data diversity. However, these approaches face limitations in ensuring style diversity due to restricted style sources, limiting the utilization of the potential style space. To address this, we propose a straightforward yet effective style conversion and generation module integrated into the UNet model. This module transfers diverse yet plausible style features to the original training data at the feature-level space, ensuring that generated styles align closely with the original data. Our method demonstrates superior performance in single-domain generalization tasks across five datasets compared to prior methods.

Classifier-guided multi-style tile image generation method

Image generative models for ceramic tile design lack style diversity and controllability of high-quality generated styles. It is difficult to find a series of ceramic tiles with the same texture but distinct styles, that makes it a challenging for users to select from a limited number of tiles with a single style. Although, Generative Adversarial Networks (GANs) can slightly increase the style diversity of tile images, the style controllability remains very weak. Additionally, concatenating generated tile image blocks to obtain a larger texture region can easily result in seams at the boundaries that decrease image quality. In this paper, we propose a style transfer method for ceramic tiles texture generation that combines a classifier-guided StyleGAN with AdaIN-GAN to overcome the above limitations. Firstly, we introduce a new conditional classifier-guided module into the StyleGAN. With the guidance of the input condition vector, the output image is made to have the tile style characteristics that match the vector. At the same time, the fusion of the condition vectors realizes the style gradient effect of the tile image to expand the style diversity. Secondly, we use the AdaIN-GAN to color the original texture in tile style. The style images generated by StyleGAN are then used as a dataset for model training to enhance the generalization ability of the model and achieve a style transfer effect with fixed texture features but significantly diverse styles. Finally, a linear weighted image stitching method is adopted, which uses an adaptive kernel linear weighted matrix to cover and splice arbitrary seams with image blocks, thereby successfully eliminating seams and enhancing image continuity. When this method is applied to high-resolution tile image generation, the method still maintains higher continuity and clearer image quality. Extensive experiments and human evaluation confirm the superior performance of the proposed method compared with other SOTA methods. The experimental results also verify that the new tile images generated by the proposed algorithm have diverse styles and meet the design requirements for tile style diversity.

On generated artistic styles: Image generation experiments with GAN algorithms

As computer graphics technology supports pursuing a photorealistic style, replicated artworks with a photorealistic style overwhelmingly predominate in the computer-generated art circle. Along with the progression of generative technology, this trend may make generative art a virtual world of photorealistic fake, in which the single criterion of expressive style imperils art into the context of a single boring stereotype. This article focuses on the issue of style diversity and its technical feasibility by artistic experiments of generating flower images in StyleGAN. The author insisted that photo both technology and artistic style should not be confined merely for realistic purposes. This proposition was validated in the GAN generation experiment by changing the training materials.

The Effects of Group Composition and Dynamics on Collective Performance.

As organizations gravitate to group-based structures, the problem of improving performance through judicious selection of group members has preoccupied scientists and managers alike. However, which individual attributes best predict group performance remains poorly understood. Here, we describe a preregistered experiment in which we simultaneously manipulated four widely studied attributes of group compositions: skill level, skill diversity, social perceptiveness, and cognitive style diversity. We find that while the average skill level of group members, skill diversity, and social perceptiveness are significant predictors of group performance, skill level dominates all other factors combined. Additionally, we explore the relationship between patterns of collaborative behavior and performance outcomes and find that any potential gains in solution quality from additional communication between the group members are outweighed by the overhead time cost, leading to lower overall efficiency. However, groups exhibiting more "turn-taking" behavior are considerably faster and thus more efficient. Finally, contrary to our expectation, we find that group compositional factors (i.e., skill level and social perceptiveness) are not associated with the amount of communication between group members nor turn-takingdynamics.

Source-free Style-diversity Adversarial Domain Adaptation with Privacy-preservation for person re-identification

Unsupervised domain adaptation (UDA) techniques for person re-identification (ReID) have been extensively studied to facilitate the transfer of knowledge from labeled source domains to unlabeled target domains. However, the need to access the source data raises privacy concerns in real-world scenarios. To overcome this limitations, source-free domain adaptation (SFDA) was introduced, enabling adaptation without requiring access to the source data, relying instead on a well-trained source model. Nevertheless, existing SFDA methods assume a shared label space and overlook the significance of domain-style discrepancies in person ReID, limiting their applicability to source-free domain adaptive person ReID. In this paper, we present a novel approach called Source-free Style-diversity Adversarial Domain Adaptation with Privacy-preservation (S2ADAP) for person ReID to address these challenges. Our approach effectively handles inter-domain pedestrian appearance style differences using GAN-based domain-style diversity augmentation and intra-domain individual style misalignment through adversarial mutual teaching learning, avoiding access to data from the source domain. We leverage a pre-trained model as a person appearance style encoder to enhance source-similar style diversity in the target domain and achieve intra-domain individual style alignment by introducing the domain style discriminator to promote the discriminability of person semantic features for domain adaptation. The experimental results on publicly available person ReID datasets affirm the efficacy of our approach, offering a promising and privacy-preserving solution for person ReID tasks.

SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text.

Large amounts of labeled data are urgently required for the training of robust text recognizers. However, collecting handwriting data of diverse styles, along with an immense lexicon, is considerably expensive. Although data synthesis is a promising way to relieve data hunger, two key issues of handwriting synthesis, namely, style representation and content embedding, remain unsolved. To this end, we propose a novel method that can synthesize parameterized and controllable handwriting S tyles for arbitrary-Length and O ut-of-vocabulary text based on a G enerative A dversarial N etwork (GAN), termed SLOGAN. Specifically, we propose a style bank to parameterize specific handwriting styles as latent vectors, which are input to a generator as style priors to achieve the corresponding handwritten styles. The training of the style bank requires only writer identification of the source images, rather than attribute annotations. Moreover, we embed the text content by providing an easily obtainable printed style image, so that the diversity of the content can be flexibly achieved by changing the input printed image. Finally, the generator is guided by dual discriminators to handle both the handwriting characteristics that appear as separated characters and in a series of cursive joins. Our method can synthesize words that are not included in the training vocabulary and with various new styles. Extensive experiments have shown that high-quality text images with great style diversity and rich vocabulary can be synthesized using our method, thereby enhancing the robustness of the recognizer.

A methodology for developing SoS architectures using SysML model federation

AbstractAn essential role of systems engineering is to aid in overcoming complexity during development. As system complexity increases, a greater number of organizations are being asked to contribute architecture/design content for systems development. An essential challenge to overcome is how to ensure digital continuity in connecting system models to form systems of systems (SoS) models. Leveraging recent developments in digital engineering (DE) and model‐based systems engineering (MBSE) this paper presents a SysML model federation methodology enabling multiple collaborating organizations to contribute system models and form a descriptive SoS architecture model. Systems engineers applying this methodology are able to reuse constituent system model content to describe the larger SoS behavior and structure while promoting reusability and commonality and are therefore better able to ensure correctness and consistency across development. First, a background through the review of SoS engineering (SoSE) and DE/MBSE literature is provided. Then an MBSE process along with specific methods tailoring the use of SysML within the Cameo Enterprise Architecture tool is presented. This work builds upon a previously published Systems Architecture Model (SAM) development method and is designed to permit style diversity across peer constituent models and ensure that every piece of data has an authoritative source of truth (ASOT) within the federation. This paper then presents the application of this methodology to the Ranger Lunar Rover system by making use of its openly published SysML model. Finally, the benefits and challenges of this methodology are discussed prior to drawing closing conclusions and identifying future areas of research.

Spatial oblivion channel attention targeting intra-class diversity feature learning

Convolutional neural networks (CNNs) have successfully driven many visual recognition tasks including image classification. However, when dealing with classification tasks with intra-class sample style diversity, the network tends to be disturbed by more diverse features, resulting in limited feature learning. In this article, a spatial oblivion channel attention (SOCA) for intra-class diversity feature learning is proposed. Specifically, SOCA performs spatial structure oblivion in a progressive regularization for each channel after convolution, so that the network is not restricted to a limited feature learning, and pays attention to more regionally detailed features. Further, SOCA reassigns channel weights in the progressively oblivious feature space from top to bottom along the channel direction, to ensure the network learns more image details in an orderly manner while not falling into feature redundancy. Experiments are conducted on the standard classification dataset CIFAR-10/100 and two garbage datasets with intra-class diverse styles. SOCA improves SqueezeNet, MobileNet, BN-VGG-19, Inception and ResNet-50 in classification accuracy by 1.31%, 1.18%, 1.57%, 2.09% and 2.27% on average, respectively. The feasibility and effectiveness of intra-class diversity feature learning in SOCA-enhanced networks are verified. Besides, the class activation map shows that more local detail feature regions are activated by adding the SOCA module, which also demonstrates the interpretability of the method for intra-class diversity feature learning.

Work Style Diversity and Diffusion Within and Across Organizations: Evidence from Soviet-Style Hockey

Does the arrival of culturally diverse workers affect the work style of incumbent workers? We examine how the large influx of Russian hockey players in the National Hockey League after 1989 affected North American–born players. The Soviet style of hockey was largely based on skilled skating, constant movement, circling, and passing. In contrast, the North American play was more individualistic and linear, with higher emphasis on physical strength and aggressive behavior. Using 50 years of data at the player-game level, we show that (i) the number of penalty minutes per game increases steadily from 1970 to 1989, but decreases thereafter; (ii) although Russian players get systematically fewer penalty minutes in and after 1989, the trend reversal is driven by North American–born players; and (iii) the number of penalty minutes per game of North American–born players decreases systematically with the number of Russian players on their team and on the opposing team. Evidence shows that the hockey style brought about by Russian players was adopted and diffused within and across North American teams and players. This paper was accepted by Lamar Pierce, organizations. Supplemental Material: Data and the online appendix are available at https://doi.org/10.1287/mnsc.2023.4808 .

Interpretations of Plot about Alceste: from Euripide’s Social and Domestic Drama to Franz Fühmann’s “Play with Music in Ancient Landscapes”

The significance of the study is due to the need to update the memory of the personality and work of the East German writer Franz Fuhmann, undeservedly forgotten in the era of united Germany. The novelty of the proposed study is due to the fact that the materials that testify to the long and painstaking preparatory work to create a play about Alces and this work itself have not only not been translated, but have not been studied in Russian German studies either. It is noted that the problem of “inclusion” of artistic consciousness in new media makes it necessary to approach the reception of the classical heritage from a new point of view. It is indicated that Franz Fuman is one of the brightest experimenters in this field. It is shown that psychological rethinking of traditional mythological situations and the creation of their new versions prevail in his dramatic experiments, which allows us to see the timeless grain of the myth. It is argued that in the named work the writer does not deviate from the formulation of the burning topics of our time, but elevates their understanding to a higher level of the eternal questions of mankind. It is emphasized that in this context it is not surprising that the writer turned to the traditions of antiquity, primarily mythology. The author of the article believes that the study of the dramatic experiments of Franz Fumann helps to supplement the picture of the genre and style diversity of his work with new facts.

Visual Attention Adversarial Networks for Chinese Font Translation

Currently, many Chinese font translation models adopt the method of dividing character components to improve the quality of generated font images. However, character components require a large amount of manual annotation to decompose characters and determine the composition of each character as input for training. In this paper, we establish a Chinese font translation model based on generative adversarial network without decomposition. First, we improve the method of image enhancement for Chinese character images. It helps the model learning structure information of Chinese character strokes to generate font images with complete and accurate strokes. Second, we propose a visual attention adversarial network. By using visual attention block, the network catches global and local features for constructing details of characters. Experiments demonstrate our method generates high-quality Chinese character images with great style diversity including calligraphy characters.

Semantic-Aware Noise Driven Portrait Synthesis and Manipulation

Semantic portrait synthesis has drawn consistent attention and has made significant progress, yet achieving style diversity and semantic controllability simultaneously is still a challenge. Existing methods either 1) directly take a semantic label map as input, ignoring various possibilities of semantic styles, or 2) sample global noise as input, ignoring controllability of local semantics. To fill this gap, we propose semantic-aware noise, a simple but effective input that tackles both issues and shows improved results over baselines. Semantic-aware noise introduces semantic information into noise, and each semantic is sampled from the noise separately, combining the semantic controllability and the noise sampling diversity. To further expand and manipulate real images, we propose a novel ternary network structure, allowing simultaneous diverse semantic image synthesis and real image manipulation in a unified framework. Extensive experiments demonstrate that the proposed method achieves quantitatively superior and perceptually pleasing results compared to state-of-the-art methods. We also analyze the performance of our method with respect to different noise structures and real-life applications in diverse synthesis, interactive manipulation, and extreme pose scenarios.

Towards better-informed dispersal probabilities in historical biogeography: Arachnids as a model lineage

Historical biogeography is an integrative scientific field critical for testing evolutionary hypotheses pertinent to organismal distributions, but despite recent theoretical and analytical advances, biogeographic reconstructions continue to struggle with accuracy and rigor. Most modern studies include the three elements needed for historical biogeographic inference, namely a time-calibrated phylogeny, contemporary taxonomic distributions, and estimations of organismal dispersal probabilities. The latter, we argue, are particularly vague, and historical biogeography would greatly benefit from dispersal probability estimations that are better informed and biologically meaningful. To achieve that goal, next-generation biogeography should ideally consider: a) dispersal-related traits; b) ecology; c) geological histories; and d) geographical factors. We briefly recap the three case studies on spiders that have pioneered this approach. Due to their old age and mega-diversity—considering both phylogenetic and life style diversity—arachnids are an ideal animal lineage for modern biogeographic research. There is no reason, however, that the concept should not be applied to all life. Further modifications of the proposed concept and, particularly, methodological implementation are needed to render this biogeographic framework widely useful.

Shape robustness in style enhanced cross domain semantic segmentation

This paper focuses on domain adaptation method based on style transfer. Previous methods based on style transfer pay attention to the transformation of texture features between domains and maintain semantic consistency to the greatest extent. However, these methods have different effects on domain gaps in different types of categories. The categories with large texture difference and small structure difference can be improved better. For the categories with small texture difference and large structure difference, it causes negative transfer. In this paper, a shape robustness enhanced domain adaptive segmentation algorithm is proposed. Firstly, we adopt adjustable style transfer methods to enhance the style diversity of source domain images. Next, we differentiated different types of image features to weaken the negative transfer in the process of adversarial training. The results of this paper on general data sets GTA5 and SYNTHIA are better than other style transfer methods. Further experiments show that we improve the shape robustness of style enhancement method in domain adaptive segmentation task.

Supporting Diverse Learning Styles: A Case Study in Student Led Syllabus Design

This paper presents a case study in student led syllabus design, geared to support diverse learning styles and to enhance student engagement. In this case, students in an Honors American Government Course participated in designing their own syllabus for the semester. This was done through a written survey in which students were able to select their preferred learning method, combination of assignments and activities, accountability mechanisms, testing structure and level of active learning. The tabulation of student responses resulted in a student designed syllabus that reflected a diversity of learning styles and a combination of passive and active learning mechanisms including traditional lecture, readings and research-based writing assignments, as well as debate, simulation and small group discussion, tailored to the preferences of the class. Student evaluations showed a high level of satisfaction with the student led syllabus design as well as with the course overall. Student participation in syllabus design allowed for differences in learning styles to be reflected in the structure of teaching mechanisms, assignments and activities, resulting in enhanced student “buy in.” This sense of ownership contributed to satisfaction, even with aspects of the course that students did not personally select, and increased levels of motivation and participation in assignments and activities. This paper will analyze the process, the outcomes, and the pros and cons of student led syllabus design as applied in this case, and evaluate its impact on learning style diversity and student engagement.

Practicing Decoloniality

Practicing Decoloniality