<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2026-26-3-466-474</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-614</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Метод геометрически-контролируемого прореживания модели сверточной нейронной сети без потери качества результата</article-title><trans-title-group xml:lang="en"><trans-title>Optimizing knowledge distillation models for language models</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-6419-0072</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Татарникова</surname><given-names>Т. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Tatarnikova</surname><given-names>T. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Татарникова Татьяна Михайловна — доктор технических наук, профессор, директор института</p><p>sc 36715607400</p><p>Санкт-Петербург, 190000</p></bio><bio xml:lang="en"><p>Tatiana M. Tatarnikova — D.Sc., Professor, Director of the Institute</p><p>sc 36715607400</p><p>Saint Petersburg, 190000</p></bio><email xlink:type="simple">tm-tatarn@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0002-0276-607X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Раскопина</surname><given-names>А. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Raskopina</surname><given-names>A. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Раскопина Анастасия Сергеевна — аспирант, ассистент</p><p>sc 59946913200</p><p>Санкт-Петербург, 190000</p></bio><bio xml:lang="en"><p>Anastasia S. Raskopina — PhD Student, Assistant</p><p>sc 59946913200</p><p>Saint Petersburg, 190000</p></bio><email xlink:type="simple">raskopina.anastasia@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный университет аэрокосмического приборостроения</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State University of Aerospace Instrumentation (SUAI)</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>09</day><month>07</month><year>2026</year></pub-date><volume>26</volume><issue>3</issue><fpage>466</fpage><lpage>474</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Татарникова Т.М., Раскопина А.С., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Татарникова Т.М., Раскопина А.С.</copyright-holder><copyright-holder xml:lang="en">Tatarnikova T.M., Raskopina A.S.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/614">https://ntv.elpub.ru/jour/article/view/614</self-uri><abstract><p>Введение. Рассмотрена задача сжатия глубоких нейронных сетей на примере сверточных нейронных сетей (Convolutional Neural Network, CNN). Размеры глубоких нейронных сетей являются препятствием для их практического применения в условиях ограниченных вычислительных ресурсов, энергии и требований задержки инференса. Одним из развиваемых направлений сжатия моделей глубоких нейронных сетей является прореживание — удаление части параметров или структурных элементов модели нейронной сети. Показано, что прореживание является компромиссом между точностью классификации и вычислительной эффективностью. Метод. Предложен метод геометрически-контролируемого прореживания модели СNN, основанный на жадном выборе степени разреженности структуры CNN при ограничении на изменение геометрии представлений. Геометрия представлений определяется через матрицу попарных косинусных сходств между центроидами классов в пространстве признаков. Оценка качества работы представленного метода получена на сравнении с методом прореживания по глубине и без прореживания модели CNN по стандартным метрикам Top-1 и Top-5 точности классификации. Оценивание степени сжатия CNN выполнено по числу параметров, объему и вычислительной сложности модели нейронной сети, а также задержки инференса. Измерения задержки инференса проводились в одинаковых условиях при фиксированном размере входных данных. Основные результаты. Выполнена разработка нового метода сжатия CNN, основанного на геометрически-контролируемом прореживании модели CNN, в котором прореживание выполняется жадно по блокам CNN, а допустимость каждого шага определяется не только локальной важностью каналов, но и глобальным ограничением на изменение геометрии представлений. Эксперимент выполнен на CNN с архитектурой ResNet-50 и обучением на стандартном наборе данных CIFAR-100 для оценки методов сжатия и ускорения CNN. Результаты проведенного эксперимента демонстрируют устойчивое сохранение качества классификации у предложенного метода при сокращении вычислительной сложности и числа параметров по сравнению с базовым методом без использования прореживания и методом прореживания по глубине модели CNN. Разработанный метод демонстрирует сопоставимую точность Top-1 и Top-5 с базовой моделью после дообучения, одновременно снижая вычислительную сложность более чем в 2,5 раза и число параметров почти в два раза. Обсуждение. Представленный метод геометрически-контролируемого прореживания модели CNN может найти применение в задачах, требующих принятия решения в реальном времени, а также на мобильных и встраиваемых устройствах.</p></abstract><trans-abstract xml:lang="en"><p>The problem of deep neural network compression is discussed using Convolutional Neural Networks (CNNs) as an example. The size of deep neural networks is an obstacle to their practical application under conditions of limited computing resources, energy, and inference latency requirements. One of the developing approaches to compressing deep neural network models is thinning-removing some of the parameters or structural elements of the neural network model. It is shown that thinning is a tradeoff between classification accuracy and computational efficiency. The problem of compressing CNN models was formulated by thinning parameters while maintaining classification quality at the level of the original model, reducing the number of parameters, computational complexity, and inference latency. Standard Top-1 and Top-5 classification accuracy metrics were used to evaluate classification quality. The degree of compression and inference latency were assessed using metrics, such as the number of model parameters, model size, computational complexity, and inference latency. To ensure a fair comparison of the proposed method with others, inference latency measurements were conducted under identical conditions with a fixed input data size. The concept of representation geometry is introduced to control the stability of the internal feature space. The change in the interclass similarity matrix, calculated from the class centroids in the feature space, is used as a metric for preserving the structure of the feature space. The main result of this work is the development of a new compression method for CNNs based on geometrically controlled thinning of the CNN model. In this method, thinning is performed greedily across CNN blocks, and the admissibility of each step is determined not only by the local importance of channels but also by a global constraint on changing the geometry of the representations. The results of the experiment demonstrate that the proposed method consistently maintains classification quality while reducing computational complexity and the number of parameters compared to the baseline method without thinning and the depth-based thinning method of the CNN model. The proposed method for geometrically controlled thinning of a CNN model can be applied to problems requiring real-time decision making as well as on mobile and embedded devices.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>глубокая нейронная сеть</kwd><kwd>число параметров обучения</kwd><kwd>прореживание модели нейросети</kwd><kwd>сжатие модели нейронной сети</kwd><kwd>геометрия представлений</kwd><kwd>вычислительная сложность</kwd><kwd>задержка инференса</kwd><kwd>качество классификации</kwd></kwd-group><kwd-group xml:lang="en"><kwd>deep neural network</kwd><kwd>number of training parameters</kwd><kwd>neural network model thinning</kwd><kwd>neural network model compression</kwd><kwd>representation geometry</kwd><kwd>computational complexity</kwd><kwd>inference delay</kwd><kwd>classification quality</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Dantas P.V., da Silva W.S., Cordeiro L.C., Carvalho C.B. A comprehensive review of model compression techniques in machine learning // Applied Intelligence. 2024. V. 54. N 22. P. 11804–11844. doi: 10.1007/s10489-024-05747-w</mixed-citation><mixed-citation xml:lang="en">Dantas P.V., da Silva W.S., Cordeiro L.C., Carvalho C.B. A comprehensive review of model compression techniques in machine learning. Applied Intelligence, 2024, vol. 54, no. 22, pp. 11804-11844. doi: 10.1007/s10489-024-05747-w</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Богачев И.В., Булканов Д.Е. Обзор современных нейросетевых методов сжатия для задачи обработки измерительных данных // Вестник Тихоокеанского государственного университета. 2024. № 2 (73). C. 83–92. doi: 10.38161/1996-3440-2024-2-83-92</mixed-citation><mixed-citation xml:lang="en">Bogachev I.V., Bulkanov D.E. Review of modern neural network compression methods for the task of processing measurement data. Bulletin of Pacific National University, 2024, no. 2 (73), pp. 83–92. (in Russian). doi: 10.38161/1996-3440-2024-2-83-92</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Татарникова Т.М., Мокрецов Н.С. Оптимизация моделей дистилляции знаний для языковых моделей // Научно-технический вестник информационных технологий, механики и оптики. 2025. Т. 25. № 4. C. 737–743. doi: 10.17586/2226-1494-2025-25-4-737-743</mixed-citation><mixed-citation xml:lang="en">Tatarnikova T.M., Mokretsov N.S. Optimizing knowledge distillation models for language models. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2025, vol. 25, no. 4, pp. 737–743. (in Russian). doi: 10.17586/2226-1494-2025-25-4-737-743</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Houlsby N., Giurgiu A., Jastrzebski S., Morrone B., de Laroussilhe Q., Gesmundo A., et al. Parameter-efficient transfer learning for NLP // Proc. of the 36th International Conference on Machine Learning. 2019. V. 97. P. 2790–2799.</mixed-citation><mixed-citation xml:lang="en">Houlsby N., Giurgiu A., Jastrzebski S., Morrone B., de Laroussilhe Q., Gesmundo A., et al. Parameter-efficient transfer learning for NLP. Proc. of the 36th International Conference on Machine Learning, 2019, vol. 97, pp. 2790–2799.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Chen J., Hu Y., Zhu J. S-STE: Continuous pruning function for efficient 2:4 sparse pre-training // Proc. of the 38th Conference on Neural Information Processing Systems (NeurIPS). 2024. P. 33756-33778. doi: 10.52202/079017-1063</mixed-citation><mixed-citation xml:lang="en">Chen J., Hu Y., Zhu J. S-STE: Continuous pruning function for efficient 2:4 sparse pre-training. Proc. of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2024, pp. 33756-33778. doi: 10.52202/079017-1063</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Frantar E., Alistarh D. SparseGPT: massive language models can be accurately pruned in one-shot // Proc. of the 40th International Conference on Machine Learning. 2023. V. 202. P. 10323–10337.</mixed-citation><mixed-citation xml:lang="en">Frantar E., Alistarh D. SparseGPT: massive language models can be accurately pruned in one-shot. Proc. of the 40th International Conference on Machine Learning, 2023, vol. 202, pp. 10323–10337.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Wang Z., Li C., Wang X. Convolutional neural network pruning with structural redundancy reduction // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021. P. 14908–14917. doi: 10.1109/cvpr46437.2021.01467</mixed-citation><mixed-citation xml:lang="en">Wang Z., Li C., Wang X. Convolutional neural network pruning with structural redundancy reduction. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 14908–14917. doi: 10.1109/cvpr46437.2021.01467</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Чернышов Н.Д., Буряк Д.Ю. Исследование влияния метода сравнения каналов на эффективность алгоритмов поканального прореживания сверточных нейронных сетей // Системный анализ в науке и образовании. 2025. № 1. C. 16–22.</mixed-citation><mixed-citation xml:lang="en">Chernyshov N.D., Buryak D.YU. Esearch into impact of channel comparison method on efficiency of algorithms for channel-wise pruning of convolutional neural networks. System Analysis in Science and Education, 2025, no. 1, pp. 16–22. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Liu D., Zhu Y., Liu Z., Liu Y., Han C., Tian J. A survey of model compression techniques: past, present, and future // Frontiers in Robotics and AI. 2025. V. 12. P. 1518965. doi: 10.3389/frobt.2025.1518965</mixed-citation><mixed-citation xml:lang="en">Liu D., Zhu Y., Liu Z., Liu Y., Han C., Tian J. A survey of model compression techniques: past, present, and future. Frontiers in Robotics and AI, 2025, vol. 12, pp. 1518965. doi: 10.3389/frobt.2025.1518965</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">He Y., Xiao L. Structured pruning for deep convolutional neural networks: A survey // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024. V. 46. N 5. P. 2900–2919. doi: 10.1109/TPAMI.2023.3334614</mixed-citation><mixed-citation xml:lang="en">He Y., Xiao L. Structured pruning for deep convolutional neural networks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, vol. 46, no. 5, pp. 2900–2919. doi: 10.1109/TPAMI.2023.3334614</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Мокрецов Н.С., Татарникова Т.М. Оптимизация процесса обучения при ограниченном объеме вычислительных ресурсов // Международная конференция по мягким вычислениям и измерениям. 2024. Т. 1. C. 205–208.</mixed-citation><mixed-citation xml:lang="en">Mokretsov N.S., Tatarnikova T.M. Optimizing the learning process with limited computational resources. International Conference on Soft Computing and Measurement, 2024, vol. 1, pp. 205–208. (in Russian)</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Lv K., Yang Y., Liu T., Guo Q., Qiu X. Full parameter fine-tuning for large language models with limited resources // Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024. V. 1. P. 8187–8198. doi: 10.18653/v1/2024.acl-long.445</mixed-citation><mixed-citation xml:lang="en">Lv K., Yang Y., Liu T., Guo Q., Qiu X. Full parameter fine-tuning for large language models with limited resources. Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics, 2024, vol. 1, pp. 8187–8198. doi: 10.18653/v1/2024.acl-long.445</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Q., Zhang R., Sun J., Liu Y. How sparse can we prune a deep network: a fundamental limit perspective // Proc. of the 38th International Conference on Neural Information Processing System. 2024. P. 91337–91372.</mixed-citation><mixed-citation xml:lang="en">Zhang Q., Zhang R., Sun J., Liu Y. How sparse can we prune a deep network: a fundamental limit perspective. Proc. of the 38th International Conference on Neural Information Processing System, 2024, pp. 91337–91372.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Cheng H., Zhang M., Shi J.Q. A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024. V. 46. N 12. P. 10558–10578. doi: 10.1109/tpami.2024.3447085</mixed-citation><mixed-citation xml:lang="en">Cheng H., Zhang M., Shi J.Q. A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, vol. 46, no. 12, pp. 10558–10578. doi: 10.1109/tpami.2024.3447085</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Zhu K., Hu F., Ding Y., Zhou W., Wang R. A comprehensive review of network pruning based on pruning granularity and pruning time perspectives // Neurocomputing. 2025. V. 626. P. 129382. doi: 10.1016/j.neucom.2025.129382</mixed-citation><mixed-citation xml:lang="en">Zhu K., Hu F., Ding Y., Zhou W., Wang R. A comprehensive review of network pruning based on pruning granularity and pruning time perspectives. Neurocomputing, 2025, vol. 626, pp. 129382. doi: 10.1016/j.neucom.2025.129382</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Кузьмин В.Н., Менисов А.Б., Сабиров Т.Р. Метод оптимизации нейронных сетей на основе структурной дистилляции с применением генетического алгоритма // Научно-технический вестник информационных технологий, механики и оптики. 2024. Т. 24. № 5. C. 770–778. doi: 10.17586/2226-1494-2024-24-5-770-778</mixed-citation><mixed-citation xml:lang="en">Kuzmin V.N., Menisov A.B., Sabirov T.R. A method for optimizing neural networks based on structural distillation using a genetic algorithm. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2024, vol. 24, no. 5, pp. 770-778. (in Russian). doi: 10.17586/2226-1494-2024-24-5-770-778</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Park C., Park M., Moon H., Yoon M.K., Go S., Kim S., et al. DEPrune: Depth-wise separable convolution pruning for maximizing GPU parallelism // Proc. of the 38th International Conference on Neural Information Processing Systems. 2024. P. 106906–106923.</mixed-citation><mixed-citation xml:lang="en">Park C., Park M., Moon H., Yoon M.K., Go S., Kim S., et al. DEPrune: Depth-wise separable convolution pruning for maximizing GPU parallelism. Proc. of the 38th International Conference on Neural Information Processing Systems, 2024, pp. 106906–106923.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Liao B., Meng Y., Monz C. Parameter-efficient fine-tuning without introducing new latency // Proc. of the 61st Annual Meeting of the Association for Computational Linguistics. 2023. V. 1. P. 4242–4260. doi: 10.18653/v1/2023.acl-long.233</mixed-citation><mixed-citation xml:lang="en">Liao B., Meng Y., Monz C. Parameter-efficient fine-tuning without introducing new latency. Proc. of the 61st Annual Meeting of the Association for Computational Linguistics, 2023, vol. 1, pp. 4242-4260. doi: 10.18653/v1/2023.acl-long.233</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Lasby M., Golubeva A., Evci U., Nica M., Ioannou Y. Dynamic sparse training with structured sparsity // Proc. of the International Conference on Learning Representations (ICLR). 2024. P. 32982-33010.</mixed-citation><mixed-citation xml:lang="en">Lasby M., Golubeva A., Evci U., Nica M., Ioannou Y. Dynamic sparse training with structured sparsity. Proc. of the International Conference on Learning Representations (ICLR), 2024, pp. 32982–33010.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Sun X., Shi H. Towards better structured pruning saliency by reorganizing convolution // Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2024. P. 2193–2203. doi: 10.1109/WACV57701.2024.00220</mixed-citation><mixed-citation xml:lang="en">Sun X., Shi H. Towards better structured pruning saliency by reorganizing convolution. Proc. of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 2193–2203. doi: 10.1109/WACV57701.2024.00220</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Wright D., Igel C., Selvan R. BMRS: Bayesian model reduction for structured pruning // Proc. of the 38th International Conference on Neural Information Processing Systems. 2024. P. 64119–64144.</mixed-citation><mixed-citation xml:lang="en">Wright D., Igel C., Selvan R. BMRS: Bayesian model reduction for structured pruning. Proc. of the 38th International Conference on Neural Information Processing Systems, 2024, pp. 64119–64144.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Dong Z., Duan Y., Zhou Y., Duan S., Hu X. Weight-adaptive channel pruning for CNNs based on closeness-centrality modeling // Applied Intelligence. 2024. V. 54. N 1. P. 201–215. doi: 10.1007/s10489-023-05164-5</mixed-citation><mixed-citation xml:lang="en">Dong Z., Duan Y., Zhou Y., Duan S., Hu X. Weight-adaptive channel pruning for CNNs based on closeness-centrality modeling. Applied Intelligence, 2024, vol. 54, no. 1, pp. 201–215. doi: 10.1007/s10489-023-05164-5</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Khan N.A., Rafat A.M.S. Pruning convolution neural networks using filter clustering based on normalized cross-correlation similarity // Journal of Information and Telecommunication. 2025. V. 9. N 2. P. 190–208. doi: 10.1080/24751839.2024.2415008</mixed-citation><mixed-citation xml:lang="en">Khan N.A., Rafat A.M.S. Pruning convolution neural networks using filter clustering based on normalized cross-correlation similarity. Journal of Information and Telecommunication, 2025, vol. 9, no. 2, pp. 190–208. doi: 10.1080/24751839.2024.2415008</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Duan Z., Lu M., Ma J., Huang Y., Ma Z., Zhu F. QARV: QuantizationAware ResNet VAE for lossy image compression // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024. V. 46. N 1. P. 436–450. doi: 10.1109/tpami.2023.3322904</mixed-citation><mixed-citation xml:lang="en">Duan Z., Lu M., Ma J., Huang Y., Ma Z., Zhu F. QARV: QuantizationAware ResNet VAE for lossy image compression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, vol. 46, no. 1, pp. 436–450. doi: 10.1109/tpami.2023.3322904</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
