Hasil untuk "Art"

Kushal Agrawal, Romi Banerjee

The intersection of generative AI and art is a fascinating area that brings both exciting opportunities and significant challenges, especially when it comes to identifying synthetic artworks. This study takes a unique approach by examining diffusion-based generative models in the context of Indian art, specifically focusing on the distinctive style of Jamini Roy. To explore this, we fine-tuned Stable Diffusion 3 and used techniques like ControlNet and IPAdapter to generate realistic images. This allowed us to create a new dataset that includes both real and AI-generated artworks, which is essential for a detailed analysis of what these models can produce. We employed various qualitative and quantitative methods, such as Fourier domain assessments and autocorrelation metrics, to uncover subtle differences between synthetic images and authentic pieces. A key takeaway from recent research is that existing methods for detecting deepfakes face considerable challenges, especially when the deepfakes are of high quality and tailored to specific cultural contexts. This highlights a critical gap in current detection technologies, particularly in light of the challenges identified above, where high-quality and culturally specific deepfakes are difficult to detect. This work not only sheds light on the increasing complexity of generative models but also sets a crucial foundation for future research aimed at effective detection of synthetic art.

Burcu Oltu, Selda Güney, Seniha Esen Yuksel et al.

Abstract Background Pulmonary diseases such as COVID-19 and pneumonia, are life-threatening conditions, that require prompt and accurate diagnosis for effective treatment. Chest X-ray (CXR) has become the most common alternative method for detecting pulmonary diseases such as COVID-19, pneumonia, and lung opacity due to their availability, cost-effectiveness, and ability to facilitate comparative analysis. However, the interpretation of CXRs is a challenging task. Methods This study presents an automated deep learning (DL) model that outperforms multiple state-of-the-art methods in diagnosing COVID-19, Lung Opacity, and Viral Pneumonia. Using a dataset of 21,165 CXRs, the proposed framework introduces a seamless combination of the Vision Transformer (ViT) for capturing long-range dependencies, DenseNet201 for powerful feature extraction, and global average pooling (GAP) for retaining critical spatial details. This combination results in a robust classification system, achieving remarkable accuracy. Results The proposed methodology delivers outstanding results across all categories: achieving 99.4% accuracy and an F1-score of 98.43% for COVID-19, 96.45% accuracy and an F1-score of 93.64% for Lung Opacity, 99.63% accuracy and an F1-score of 97.05% for Viral Pneumonia, and 95.97% accuracy with an F1-score of 95.87% for Normal subjects. Conclusion The proposed framework achieves a remarkable overall accuracy of 97.87%, surpassing several state-of-the-art methods with reproducible and objective outcomes. To ensure robustness and minimize variability in train-test splits, our study employs five-fold cross-validation, providing reliable and consistent performance evaluation. For transparency and to facilitate future comparisons, the specific training and testing splits have been made publicly accessible. Furthermore, Grad-CAM-based visualizations are integrated to enhance the interpretability of the model, offering valuable insights into its decision-making process. This innovative framework not only boosts classification accuracy but also sets a new benchmark in CXR-based disease diagnosis.

Srinitish Srinivasan, Varenya Pathak, Abirami S

Abstract Art is an immensely popular, discussed form of art that often has the ability to depict the emotions of an artist. Many researchers have made attempts to study abstract art in the form of edge detection, brush stroke and emotion recognition algorithms using machine and deep learning. This papers describes the study of a wide distribution of abstract paintings using Generative Adversarial Neural Networks(GAN). GANs have the ability to learn and reproduce a distribution enabling researchers and scientists to effectively explore and study the generated image space. However, the challenge lies in developing an efficient GAN architecture that overcomes common training pitfalls. This paper addresses this challenge by introducing a modified-DCGAN (mDCGAN) specifically designed for high-quality artwork generation. The approach involves a thorough exploration of the modifications made, delving into the intricate workings of DCGANs, optimisation techniques, and regularisation methods aimed at improving stability and realism in art generation enabling effective study of generated patterns. The proposed mDCGAN incorporates meticulous adjustments in layer configurations and architectural choices, offering tailored solutions to the unique demands of art generation while effectively combating issues like mode collapse and gradient vanishing. Further this paper explores the generated latent space by performing random walks to understand vector relationships between brush strokes and colours in the abstract art space and a statistical analysis of unstable outputs after a certain period of GAN training and compare its significant difference. These findings validate the effectiveness of the proposed approach, emphasising its potential to revolutionise the field of digital art generation and digital art ecosystem.

Hui Ren, Joanna Materzynska, Rohit Gandikota et al.

We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-image model exclusively on photographs, without access to any painting-related content. We show that it is possible to adapt a model that is trained without paintings to an artistic style, given only few examples. User studies and automatic evaluations confirm that our model (post-adaptation) performs on par with state-of-the-art models trained on massive datasets that contain artistic content like paintings, drawings or illustrations. Finally, using data attribution techniques, we analyze how both artistic and non-artistic datasets contribute to generating artistic-style images. Surprisingly, our findings suggest that high-quality artistic outputs can be achieved without prior exposure to artistic data, indicating that artistic style generation can occur in a controlled, opt-in manner using only a limited, carefully selected set of training examples.

Sze Sing Lee

Conventional 5-level active neutral-point-clamped (5L-ANPC) topology and state-of-the-art 5-level hybrid active neutral-point-clamped (5L-HANPC) topology are popular for inverter applications. However, their dc-link voltage utilization is limited to only 50%. With the maximum voltage level generated by only half dc-link voltage, these inverters are not capable of boosting voltage in their ac output. To resolve these drawbacks, this paper proposes a family of four novel 5-level boost-active neutral-point-clamped (5L-BANPC) inverters. Without requiring any flying capacitors, the proposed topologies can generate five voltage levels by effectively using the dc-link capacitors. The dc-link voltage utilization of the proposed 5L-BANPC inverters is twice that of the 5L-ANPC and 5L-HANPC topologies. While generating the five-level ac output voltage, natural voltage balancing of both dc-link capacitors and voltage boosting are achieved. Ease of implementation is another noteworthy merit of the proposed 5L-BANPC inverters because they can be implemented using six widely available commercial half-bridge modules without requiring a dedicated circuit design. The operation of the proposed topologies is analyzed. Experimental results are presented for verification.

Feng-Chou Cheng, Ling-Hsia Wang, Mu-Hsiung Chen et al.

George A. Vouros

Interpretability, explainability and transparency are key issues to introducing Artificial Intelligence methods in many critical domains: This is important due to ethical concerns and trust issues strongly connected to reliability, robustness, auditability and fairness, and has important consequences towards keeping the human in the loop in high levels of automation, especially in critical cases for decision making, where both (human and the machine) play important roles. While the research community has given much attention to explainability of closed (or black) prediction boxes, there are tremendous needs for explainability of closed-box methods that support agents to act autonomously in the real world. Reinforcement learning methods, and especially their deep versions, are such closed-box methods. In this article we aim to provide a review of state of the art methods for explainable deep reinforcement learning methods, taking also into account the needs of human operators - i.e., of those that take the actual and critical decisions in solving real-world problems. We provide a formal specification of the deep reinforcement learning explainability problems, and we identify the necessary components of a general explainable reinforcement learning framework. Based on these, we provide a comprehensive review of state of the art methods, categorizing them in classes according to the paradigm they follow, the interpretable models they use, and the surface representation of explanations provided. The article concludes identifying open questions and important challenges.

Kumar Shridhar, Koustuv Sinha, Andrew Cohen et al.

In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and correct the errors in their generations when asked to do so. However, recent empirical evidence points in the opposite direction, suggesting that LLMs often struggle to accurately identify errors when reasoning is involved. To address this, we propose a reasoning with refinement objective called ART: Ask, Refine, and Trust, which asks necessary questions to decide when an LLM should refine its output, and either affirm or withhold trust in its refinement by ranking the refinement and the initial prediction. On two multistep reasoning tasks of mathematical word problems (GSM8K) and question answering (StrategyQA), ART achieves a performance gain of +5 points over self-refinement baselines, while using a much smaller model as the decision maker. We also demonstrate the benefit of using smaller models to make refinement decisions as a cost-effective alternative to fine-tuning a larger model.

Mark Carney

This paper describes how to `Free the Qubit' for art, by creating standalone quantum musical effects and instruments. Previously released quantum simulator code for an ARM-based Raspberry Pi Pico embedded microcontroller is utilised here, and several examples are built demonstrating different methods of utilising embedded resources: The first is a Quantum MIDI processor that generates additional notes for accompaniment and unique quantum generated instruments based on the input notes, decoded and passed through a quantum circuit in an embedded simulator. The second is a Quantum Distortion module that changes an instrument's raw sound according to a quantum circuit, which is presented in two forms; a self-contained Quantum Stylophone, and an effect module plugin called 'QubitCrusher' for the Korg Nu:Tekt NTS-1. This paper also discusses future work and directions for quantum instruments, and provides all examples as open source. This is, to the author's knowledge, the first example of embedded Quantum Simulators for Instruments of Music (another QSIM).

Ian Amanya, Michael Muhoozi, Dickson Aruhomukama et al.

<h4>Background</h4>Isoniazid preventive therapy (IPT) is given to HIV patients to reduce the risk of active tuberculosis (TB). However, treatment completion remains suboptimal among those that are initiated. This study aimed to determine the completion level of IPT and the factors associated with non-completion among patients on antiretroviral therapy (ART) at Kisenyi Health Center IV in Kampala, Uganda.<h4>Methods</h4>A mixed-methods facility-based retrospective cohort study utilizing routinely collected data from 341 randomly selected HIV patients initiated on IPT was conducted. Data extracted from the registers was used to determine IPT completion. Robust Poisson regression was conducted to determine the associated factors of IPT non-completion, while in-depth interviews were conducted to explore barriers to IPT completion from the patient's perspective.<h4>Results</h4>A total of 341 patients who started on isoniazid (INH) were retrospectively followed up, with 69% (236/341) being female. Overall IPT completion was 83%. Multivariate analysis revealed the prevalence of IPT non-completion among males was 2.24 times the prevalence among females (aPR 2.24, 95% CI: 1.40-3.58, p = 0.001). The prevalence of IPT non-completion among patients with a non-suppressed HIV viral load was 3.00 times the prevalence among those with a suppressed HIV viral load (aPR 3.00, 95% CI: 1.44-6.65, p = 0.007). The prevalence of IPT non-completion among patients who were married, or cohabiting was 0.31 times the prevalence among those who were single (aPR 0.31, 95% CI: 0.17-0.55, p<0.000). Lack of IPT-related health education, pill burden, distance to the health facility, and patient relocation were reported as barriers to IPT completion.<h4>Conclusion</h4>IPT completion was found to be 83% among the cohort studied. However, lower completion levels persist among males and HIV-virally non-suppressed patients. Lack of IPT-related health education, pill burden, distance to the health facility, and patient relocation were reported as barriers to IPT completion. Interventions that target these groups of people need to be intensified.

Marisse Nepomuceno, Cybele Lara Abad, Edsel Maurice Salvaña

<h4>Introduction</h4>The HIV care cascade is a model used to examine the engagement of people living with HIV (PLHIV) in medical care from the time of diagnosis to sustained viral suppression. This study describes the stages of the cascade from linkage to care, antiretroviral therapy (ART) initiation, retention in care, and virologic suppression- at the University of the Philippines-Philippine General Hospital (UP-PGH) STD/AIDS Guidance and Intervention Prevention (SAGIP) treatment hub in the context of existing cascades with similar demographics.<h4>Methods</h4>We retrospectively reviewed the medical records of patients enrolled at the UP-PGH SAGIP treatment hub from June 2015 to December 2017. Baseline demographic and clinical data were collected, relevant to each stage of the cascade. Descriptive statistics using Microsoft Excel version 16.0 was used to characterize data and cumulative and conditional proportions were reported.<h4>Results</h4>Of the 584 patients included in the cohort, majority were male (91.1%), with a median age of 29 years (range, 0.17 to 68 years). Male-to-male sex was the most common mode of transmission (325/584, 55.6%). Among all patients enrolled at the UP PGH SAGIP treatment hub, 99.5% were linked to care, 95.0% initiated ART, 78.8% were retained in care and maintained on ART, 47.9% were tested for HIV viral load, and 45.5% achieved viral suppression.<h4>Conclusion</h4>A high proportion of patients enrolled at the UP-PGH SAGIP treatment hub are linked to care and initiate ART, exceeding the set goal of 90%, which is higher than reported nationwide. However, there is a substantial decrease in the number of patients who are subsequently retained in care, tested for HIV viral load, and achieve viral suppression. Gaps in the cascade related to healthcare delivery need to be investigated further and addressed by future studies. We recommend implementation of a community-based, patient-centered approach in order to reach the goals of the HIV cascade, with particular focus on young, MSM-PLHIV.

Anna Haensch, Dina Deitsch

Public art shapes our shared spaces. Public art should speak to community and context, and yet, recent work has demonstrated numerous instances of art in prominent institutions favoring outdated cultural norms and legacy communities. Motivated by this, we develop a novel recommender system to curate public art exhibits with built-in equity objectives and a local value-based allocation of constrained resources. We develop a cost matrix by drawing on Schelling's model of segregation. Using the cost matrix as an input, the scoring function is optimized via a projected gradient descent to obtain a soft assignment matrix. Our optimization program allocates artwork to public spaces in a way that de-prioritizes "in-group" preferences, by satisfying minimum representation and exposure criteria. We draw on existing literature to develop a fairness metric for our algorithmic output, and we assess the effectiveness of our approach and discuss its potential pitfalls from both a curatorial and equity standpoint.

Yifan Wang, Nan Li, Suxuan Jiang et al.

The application of data visualization in public art attracts increasing attention. In this paper, we present the design and implementation of a visualization method for sunlight data collected over a long period of time with an industrial camera. The proposed method makes use of the saturation and value information of collected sunlight image data in Hue Saturation Value color model to show the variation of the mood of the sunlight. Specifically, we create visual patterns with a rotating planet gear, which has an intuitively consistent geometric meaning with HSV color model and the planetary motion. Due to the variation of the sunlight data over time, the generated visual pattern presents a periodic variation that corresponds to the changing mood of the sunlight. Furthermore, we also use the sunlight data to generate music as another form of data representation. Two public artworks have been created with the above visualization and auralization methods and displayed on an exhibition held at China Resources Tower, Shenzhen, China. This work is a typical practice of creating public installations with data visualization technology, giving a glimpse into the many ways science and art intersect.

Roberto Bigazzi, Federico Landi, Silvia Cascianelli et al.

Embodied agents, trained to explore and navigate indoor photorealistic environments, have achieved impressive results on standard datasets and benchmarks. So far, experiments and evaluations have involved domestic and working scenes like offices, flats, and houses. In this paper, we build and release a new 3D space with unique characteristics: the one of a complete art museum. We name this environment ArtGallery3D (AG3D). Compared with existing 3D scenes, the collected space is ampler, richer in visual features, and provides very sparse occupancy information. This feature is challenging for occupancy-based agents which are usually trained in crowded domestic environments with plenty of occupancy information. Additionally, we annotate the coordinates of the main points of interest inside the museum, such as paintings, statues, and other items. Thanks to this manual process, we deliver a new benchmark for PointGoal navigation inside this new space. Trajectories in this dataset are far more complex and lengthy than existing ground-truth paths for navigation in Gibson and Matterport3D. We carry on extensive experimental evaluation using our new space for evaluation and prove that existing methods hardly adapt to this scenario. As such, we believe that the availability of this 3D model will foster future research and help improve existing solutions.

Georg Bökman, Fredrik Kahl

The aim of this paper is to demonstrate that a state of the art feature matcher (LoFTR) can be made more robust to rotations by simply replacing the backbone CNN with a steerable CNN which is equivariant to translations and image rotations. It is experimentally shown that this boost is obtained without reducing performance on ordinary illumination and viewpoint matching sequences.

Simon Batzner, Albert Musaelian, Lixin Sun et al.

An E(3)-equivariant deep learning interatomic potential is introduced for accelerating molecular dynamics simulations. The method obtains state-of-the-art accuracy, can faithfully describe dynamics of complex systems with remarkable sample efficiency.

Yanhan Li, Lian Zou, Li Xiong et al.

Automated segmentation and evaluation of carotid plaques ultrasound images is of great significance for the diagnosis and early intervention of high-risk groups of cardiovascular and cerebrovascular diseases. However, it remains challenging to develop such solutions due to the relatively low quality of ultrasound images and heterogenous characteristics of carotid plaques. To address those problems, in this paper, we propose a novel deep convolutional neural network, FRDD-Net, with an encoder–decoder architecture to automatically segment carotid plaques. We propose the feature remapping modules (FRMs) and incorporate them into the encoding and decoding blocks to ameliorate the reliability of acquired features. We also propose a new dense decoding mechanism as part of the decoder, thus promoting the utilization efficiency of encoded features. Additionally, we construct a compound loss function to train our network to further enhance its robustness in the face of numerous cases. We train and test our network in multiple carotid plaque ultrasound datasets and our method yields the best performance compared to other state-of-the-art methods. Further ablation studies consistently show the advancement of our proposed architecture.

Theodoros Galanos, Antonios Liapis, Georgios N. Yannakakis

This paper introduces a novel method for generating artistic images that express particular affective states. Leveraging state-of-the-art deep learning methods for visual generation (through generative adversarial networks), semantic models from OpenAI, and the annotated dataset of the visual art encyclopedia WikiArt, our AffectGAN model is able to generate images based on specific or broad semantic prompts and intended affective outcomes. A small dataset of 32 images generated by AffectGAN is annotated by 50 participants in terms of the particular emotion they elicit, as well as their quality and novelty. Results show that for most instances the intended emotion used as a prompt for image generation matches the participants' responses. This small-scale study brings forth a new vision towards blending affective computing with computational creativity, enabling generative systems with intentionality in terms of the emotions they wish their output to elicit.

Nahyun Kwon, Yunjung Lee, Uran Oh

While people with visual impairments are interested in artwork as much as their sighted peers, their experience is limited to few selective artworks that are exhibited at certain museums. To enable people with visual impairments to access and appreciate as many artworks as possible at ease, we propose an online art gallery that allows users to explore different parts of a painting displayed on their touchscreen-based devices while listening to corresponding verbal descriptions of the touched part on the screen. To investigate the scalability of our approach, we first explored if anonymous crowd who may not have expertise in art are capable of providing visual descriptions of artwork as a preliminary study. Then we conducted a user study with 9 participants with visual impairments to explore the potential of our system for independent artwork appreciation by assessing if and how well the system supports 4 steps of Feldman Model of Criticism. The findings suggest that visual descriptions of artworks produced by an anonymous crowd are sufficient for people with visual impairments to interpret and appreciate paintings with their own judgments which is different from existing approaches that focused on delivering descriptions and opinions written by art experts. Based on the lessons learned from the study, we plan to collect visual descriptions of a greater number of artwork and distribute our online art gallery publicly to make more paintings accessible for people with visual impairments.

Chrisantha Fernando, S. M. Ali Eslami, Jean-Baptiste Alayrac et al.

Whilst there are perhaps only a few scientific methods, there seem to be almost as many artistic methods as there are artists. Artistic processes appear to inhabit the highest order of open-endedness. To begin to understand some of the processes of art making it is helpful to try to automate them even partially. In this paper, a novel algorithm for producing generative art is described which allows a user to input a text string, and which in a creative response to this string, outputs an image which interprets that string. It does so by evolving images using a hierarchical neural Lindenmeyer system, and evaluating these images along the way using an image text dual encoder trained on billions of images and their associated text from the internet. In doing so we have access to and control over an instance of an artistic process, allowing analysis of which aspects of the artistic process become the task of the algorithm, and which elements remain the responsibility of the artist.