Doklady Mathematics最新文献_第5页

Deforming Implicit Neural Representation Generative Adversarial Network for Unsupervised Appearence Editing

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602373

S. Ignatiev, V. Egiazarian, R. Rakhimov, E. Burnaev

{"title":"Deforming Implicit Neural Representation Generative Adversarial Network for Unsupervised Appearence Editing","authors":"S. Ignatiev, V. Egiazarian, R. Rakhimov, E. Burnaev","doi":"10.1134/S1064562424602373","DOIUrl":"10.1134/S1064562424602373","url":null,"abstract":"In this work, we present a new deep generative model for disentangling image shape from its appearance through differentiable warping. We propose to use implicit neural representations for modeling the deformation field and show that coordinate-based representations hold the necessary inductive bias. Unlike the previous warping-based approaches, which tend to model only local and small-scale displacements, our method is able to learn complex deformations and is not restricted to reversible mappings. We study the convergence of warping-based generative models and find that the high-frequency nature of the textures leads to shattered learning gradients, slow convergence, and suboptimal solutions. To cope with this problem, we propose to use invertible blurring, which smooths the gradients and leads to improved results. As a way to further facilitate the convergence of warping, we train the deformation module jointly as a vanilla GAN generator to guide the learning process in a self-distillation manner. Our complete pipeline shows decent results on the LSUN churches dataset. Finally, we demonstrate various applications of our model, like composable texture editing, controllable deformation editing, and keypoint detection.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"110 1 supplement","pages":"S299 - S311"},"PeriodicalIF":0.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S1064562424602373.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation CRAFT：以俄语文化为导向的数据集改编，用于文本到图像的集中生成

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602324

V. A. Vasilev, V. S. Arkhipkin, J. D. Agafonova, T. V. Nikulina, E. O. Mironova, A. A. Shichanina, N. A. Gerasimenko, M. A. Shoytov, D. V. Dimitrov

{"title":"CRAFT: Cultural Russian-Oriented Dataset Adaptation for Focused Text-to-Image Generation","authors":"V. A. Vasilev, V. S. Arkhipkin, J. D. Agafonova, T. V. Nikulina, E. O. Mironova, A. A. Shichanina, N. A. Gerasimenko, M. A. Shoytov, D. V. Dimitrov","doi":"10.1134/S1064562424602324","DOIUrl":"10.1134/S1064562424602324","url":null,"abstract":"Despite the fact that popular text-to-image generation models cope well with international and general cultural queries, they have a significant knowledge gap regarding individual cultures. This is due to the content of existing large training datasets collected on the Internet, which are predominantly based on Western European or American popular culture. Meanwhile, the lack of cultural adaptation of the model can lead to incorrect results, a decrease in the generation quality, and the spread of stereotypes and offensive content. In an effort to address this issue, we examine the concept of cultural code and recognize the critical importance of its understanding by modern image generation models, an issue that has not been sufficiently addressed in the research community to date. We propose the methodology for collecting and processing the data necessary to form a dataset based on the cultural code, in particular the Russian one. We explore how the collected data affects the quality of generations in the national domain and analyze the effectiveness of our approach using the Kandinsky 3.1 text-to-image model. Human evaluation results demonstrate an increase in the level of awareness of Russian culture in the model.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"110 1 supplement","pages":"S137 - S150"},"PeriodicalIF":0.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SwiftDepth++: An Efficient and Lightweight Model for Accurate Depth Estimation SwiftDepth++：用于精确深度估计的高效轻量级模型

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602038

Y. Dayoub, I. Makarov

{"title":"SwiftDepth++: An Efficient and Lightweight Model for Accurate Depth Estimation","authors":"Y. Dayoub, I. Makarov","doi":"10.1134/S1064562424602038","DOIUrl":"10.1134/S1064562424602038","url":null,"abstract":"Depth estimation is a crucial task across various domains, but the high cost of collecting labeled depth data has led to growing interest in self-supervised monocular depth estimation methods. In this paper, we introduce SwiftDepth++, a lightweight depth estimation model that delivers competitive results while maintaining a low computational budget. The core innovation of SwiftDepth++ lies in its novel depth decoder, which enhances efficiency by rapidly compressing features while preserving essential information. Additionally, we incorporate a teacher-student knowledge distillation framework that guides the student model in refining its predictions. We evaluate SwiftDepth++ on the KITTI and NYU datasets, where it achieves an absolute relative error (Abs_rel) of 10.2% on the KITTI dataset and 22% on the NYU dataset without fine-tuning, all with approximately 6 million parameters. These results demonstrate that SwiftDepth++ not only meets the demands of modern depth estimation tasks but also significantly reduces computational complexity, making it a practical choice for real-world applications.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"110 1 supplement","pages":"S162 - S171"},"PeriodicalIF":0.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S1064562424602038.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hiding Backdoors within Event Sequence Data via Poisoning Attacks 通过中毒攻击在事件序列数据中隐藏后门

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602221

A. Ermilova, E. Kovtun, D. Berestnev, A. Zaytsev

引用次数: 0

Rethinking Graph Classification Problem in Presence of Isomorphism

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602385

S. Ivanov, S. Sviridov, E. Burnaev

引用次数: 0

RuSciBench: Open Benchmark for Russian and English Scientific Document Representations

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602191

A. Vatolin, N. Gerasimenko, A. Ianina, K. Vorontsov

引用次数: 0

Multimodal 3D Map Reconstruction for Intelligent Robotcs Using Neural Network-Based Methods

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602014

D. A. Yudin

引用次数: 0

Stack More LLM’s: Efficient Detection of Machine-Generated Texts via Perplexity Approximation 堆栈更多的 LLM：通过易错性近似高效检测机器生成的文本

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602075

G. M. Gritsai, I. A. Khabutdinov, A. V. Grabovoy

{"title":"Stack More LLM’s: Efficient Detection of Machine-Generated Texts via Perplexity Approximation","authors":"G. M. Gritsai, I. A. Khabutdinov, A. V. Grabovoy","doi":"10.1134/S1064562424602075","DOIUrl":"10.1134/S1064562424602075","url":null,"abstract":"The development of large language models (LLMs) is currently receiving a great amount of interest, but an update of text generation methods should entail a continuous update of methods for detecting machine-generated texts. Earlier, it has been highlighted that values of perplexity and log-probability are able to capture a measure of the difference between artificial and human-written texts. Using this observation, we define a new criterion based on these two values to judge whether a passage is generated from a given LLM. In this paper, we propose a novel efficient method that enables the detection of machine-generated fragments using an approximation of the LLM perplexity value based on pre-collected statistical language models. Approximation lends a hand in achieving high performance and quality metrics also on fragments from weights-closed LLMs. A large number of pre-collected statistical dictionaries results in an increased generalisation ability and the possibility to cover text sequences from the wild. Such approach is easy to update by only adding a new dictionary with latest model text outputs. The presented method has a high performance and achieves quality with an average of 94% recall in detecting generated fragments among texts from various open-source LLMs. In addition, the method is able to perform in milliseconds, which outperforms state-of-the-art models by a factor of thousands.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"110 1 supplement","pages":"S203 - S211"},"PeriodicalIF":0.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S1064562424602075.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An Empirical Scrutinization of Four Crisp Clustering Methods with Four Distance Metrics and One Straightforward Interpretation Rule 用四种距离度量和一种直接解释规则对四种简洁聚类方法进行实证检验

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S1064562424602002

T. A. Alvandyan, S. Shalileh

引用次数: 0

About Modifications of the Loss Function for the Causal Training of Physics-Informed Neural Networks

IF 0.5 4区数学

Doklady Mathematics Pub Date : 2025-03-22 DOI: 10.1134/S106456242460194X

V. A. Es’kin, D. V. Davydov, E. D. Egorova, A. O. Malkhanov, M. A. Akhukov, M. E. Smorkalov

{"title":"About Modifications of the Loss Function for the Causal Training of Physics-Informed Neural Networks","authors":"V. A. Es’kin, D. V. Davydov, E. D. Egorova, A. O. Malkhanov, M. A. Akhukov, M. E. Smorkalov","doi":"10.1134/S106456242460194X","DOIUrl":"10.1134/S106456242460194X","url":null,"abstract":"A method is presented that allows to reduce a problem described by differential equations with initial and boundary conditions to a problem described only by differential equations which encapsulate initial and boundary conditions. It becomes possible to represent the loss function for physics-informed neural networks (PINNs) methodology in the form of a single term associated with modified differential equations. Thus eliminating the need to tune the scaling coefficients for the terms of loss function related to boundary and initial conditions. The weighted loss functions respecting causality were modified and new weighted loss functions, based on generalized functions, are derived. Numerical experiments have been carried out for a number of problems, demonstrating the accuracy of the proposed approaches. The neural network architecture was proposed for the Korteweg–De Vries equation, which is more relevant for this problem under consideration, and it demonstrates superior extrapolation of the solution in the space-time domain where training was not performed.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"110 1 supplement","pages":"S172 - S192"},"PeriodicalIF":0.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S106456242460194X.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0