• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Efficient Pruning Optimization for Trainable Descriptor-Based Facade Signboard Classification
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2028
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
September 22, 2026
Personal Interest in Doctoral Thesis Topic Most Important for Confidence in Successful Defence
A researcher at HSE University analysed data on 1,539 doctoral students from 161 Russian universities to identify which features of a thesis topic are associated with academic success and engagement. The most important factor was found to be personal interest in the research topic, which was associated with almost all key aspects of doctoral programme experience—from engaging with the academic supervisor to research activity and confidence about successfully defending the thesis. The findings have been published in Higher Education.
September 21, 2026
Researchers Develop Methodology to Assess the Quality of Legal Representation in Criminal Proceedings
Having a good defence attorney in criminal proceedings can largely determine whether a defendant retains their freedom, health and good name. Researchers at HSE University propose a method for predicting an attorney’s performance based on the outcomes of their previous cases. The methodology takes into account the severity of the charges, the complexity of the cases, and the most likely outcome, drawing on judicial statistics.
September 21, 2026
Algebra, Geometry, and AI: Russian and Vietnamese Mathematicians Discuss Current Research
A delegation of scientists from Hanoi visited the HSE Faculty of Computer Science and then took part in a Russian-Vietnamese conference in St Petersburg. The events were part of the three-year project ‘Flexibility and Computational Methods.’ Over the course of the project, the researchers have prepared joint publications and obtained new mathematical results.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

Efficient Pruning Optimization for Trainable Descriptor-Based Facade Signboard Classification

P. 253–261.
Aleksei Samarin, Aleksei Toropov, Nazarenko A., Kotenko E., Mamaeva A., Nazarenko D., Elena Mikhailova, Valentin Malykh, Alexander Savelev, Motyko A.

Commercial facade service classification from streetlevel imagery benefits from multi-branch pipelines that fuse global facade appearance with signboard-centric cues; however, this design increases inference cost and hinders large-scale deployment. We study pruning for a multi-branch facade recognition pipeline with a trainable signboard descriptor and compare unstructured magnitude pruning with structured baselines, including channel pruning and latency-aware structured pruning. We further propose a customized, architecture-aware pruning strategy that allocates sparsity across modules according to their sensitivity and computational profile. Experiments on a curated Google Street View subset and the Signboard Classification Dataset show that unstructured pruning reduces parameters, but yields limited wall-clock speedup, whereas structured pruning provides substantial acceleration. At 50% sparsity, the proposed method reduces latency from 14.3 ms to 7.9 ms and FLOPs from 2.83G to 1.26G while preserving macro-averaged F1-score close to the baseline (0.836 vs. 0.844 on GSV; 0.878 vs. 0.887 on SCD). At 60% sparsity, it further reduces latency to 6.9 ms and FLOPs to 1.04G with competitive performance (0.826 on GSV; 0.868 on SCD). Overall, the proposed strategy improves the accuracy– efficiency trade-off of facade service recognition under realistic domain variability.

Language: English
DOI
Text on another site
Keywords: deep learningmodel pruningfacade classificationsignboard classificationvisual descriptors

In book

Proceedings of the 39th Conference of Open Innovations Association FRUCT
Vol. 39. , FRUCT Oy, 2026.
Similar publications
Lightweight Image Preprocessing Model for Improving Microorganism Detection in Microscopic Scenes
Самарин А. В., Торопов А. Г., Савельев А. Г. et al., Pattern Recognition and Image Analysis 2024 Vol. 34 No. 4 P. 1044–1052
This paper presents a study aimed at improving the detection quality of small-sized microorganisms under challenging microscopic conditions through the application of a lightweight combined image preprocessing model. We focused on the task of detecting diplococci in images obtained through dynamic sample microscopy. The proposed approach employs predefined filters for image preprocessing, combined with the ...
Added: September 21, 2026
Advancements in Signal, Image and Video Processing
Singapore: Springer Singapore, 2025.
Added: September 21, 2026
IDAP++: Advancing Divergence-Based Pruning via Filter-Level and Layer-Level Optimization
Aleksei Samarin, Nazarenko A., Kotenko E. et al., / Series arXiv "math". 2025. No. 2511.20141.
This paper presents a novel approach to neural network compression that addresses redundancy at both the filter and architectural levels through a unified framework grounded in information flow analysis. Building on the concept of tensor flow divergence, which quantifies how information is transformed across network layers, we develop a two-stage optimization process. The first stage ...
Added: September 21, 2026
Pattern Recognition. ICPR 2024 International Workshops and Challenges
Springer, Cham, 2025.
Added: September 21, 2026
Advances in Neural Computation, Machine Learning, and Cognitive Research IX
Springer, Cham, 2026.
computer vision ...
Added: September 19, 2026
Proceedings of 18th International Conference on Machine Learning and Computing
Springer, Cham, 2026.
Added: September 19, 2026
Proceedings of the 35th Conference of Open Innovations Association FRUCT, Tampere, Finland, 24-26 April 2024
FRUCT Oy, 2024.
Added: September 19, 2026
AutoML Applications for Bacilli Recognition by Taxonomic Characteristics Determination over Microscopic Images
Aleksei Samarin, Aleksei Toropov, Dzestelova A. et al., , in: Proceedings of the 36th Conference of Open Innovations Association FRUCT, Helsinki, Finland, 30 October - 1 November 2024Vol. 36.: FRUCT Oy, 2024. P. 903–911.
In this work, we describe our research aimed at developing classifiers for microbial images (bacilli images) obtained through microscopy of live (non-static) samples. We employed our proposed approach called AutoML, which is based on the automatic generation and analysis of the feature space to create the most optimal descriptors for microscopic images used in their ...
Added: September 19, 2026
Proceedings of the 36th Conference of Open Innovations Association FRUCT, Helsinki, Finland, 30 October - 1 November 2024
FRUCT Oy, 2024.
Added: September 19, 2026
Proceedings of the 37th Conference of Open Innovations Association FRUCT
FRUCT Oy, 2025.
Added: September 19, 2026
Adaptive Pruning for Universal-Filter Image Color Correction
Aleksei Samarin, Aleksei Toropov, Nazarenko A. et al., , in: Proceedings of the 39th Conference of Open Innovations Association FRUCTVol. 39.: FRUCT Oy, 2026. P. 244–252.
Universal-filter-based models provide an efficient and interpretable framework for image color correction by predicting parameters of structured correction operators. However, practical deployment still benefits from additional reductions in computational cost and memory footprint, especially for ondevice and real-time pipelines where color stability is perceptually critical. In this work, we study pruning for a universal-filter color ...
Added: September 19, 2026
Optimized Pruning Strategies for Non-Local Architectures in Lung Computed Tomography Tumor Recognition
Aleksei Samarin, Aleksei Toropov, Nazarenko A. et al., , in: Proceedings of the 39th Conference of Open Innovations Association FRUCTVol. 39.: FRUCT Oy, 2026. P. 262–270.
Attention-augmented encoder-decoder models with non-local modules are effective for lung tumor analysis on computed tomography (CT), yet their computational and memory demands can hinder deployment. We study pruning for a specialized non-local U-Net pipeline that jointly performs neoplasm presence recognition and lesion segmentation from single-channel CT snapshots. We benchmark unstructured and structured pruning baselines and ...
Added: September 19, 2026
Proceedings of the 39th Conference of Open Innovations Association FRUCT
FRUCT Oy, 2026.
Added: September 19, 2026
Refined Non-Local Blocks for Precise Segmentation of Diplococci in Microscopy Imagery
Aleksei Samarin, Kotenko E., Aleksei Toropov et al., , in: ICICT 2026: Proceedings of the 2026 9th International Conference on Information and Computer Technologies.: Association for Computing Machinery (ACM), 2026. P. 155–161.
This study investigates the integration of attention mechanisms within deep learning architectures, specifically focusing on the segmentation of diplococci microorganisms in microscopy images. We introduce novel modifications to attention blocks, tailored to address challenges inherent to microscopy imaging, such as blurred boundaries and indistinct microorganism features. Our experimental results demonstrate significant performance improvements compared to ...
Added: September 19, 2026
Flow-Guided Neural Pruning: Signal-Flow Framework for Multi-Architecture Model Compression
Aleksei Samarin, Nazarenko A., Kotenko E. et al., Machine Learning and Knowledge Extraction 2026 Vol. 8 No. 8 P. 1–26
This paper presents a novel method for pruning deep neural networks based on the concept of flow, derived from the continuous modeling of signal propagation across layers. We derive flow functions for fully connected, convolutional, and self-attention architectures, and we propose a new iterative pruning algorithm, Iterative Flow-Aware Pruning (IFAP), that leverages these measures to ...
Added: September 19, 2026
Explainable Glaucoma Screening via Optic Disc Localization and Comparative Class Activation Map-Based Analysis
Ramos-Soto O., Perez-Zarate E., Ramos-Frutos J. et al., Machine Learning and Knowledge Extraction 2026 Vol. 8 No. 7 Article 173
Added: September 18, 2026
Применение технологий компьютерного зрения в системах обработки визуальной информации
Lebedev O. B., Черкасов Р. И., Известия ЮФУ. Технические науки 2025 № 5(247) С. 254–276
This paper considers the application of artificial intelligence technologies, in particular computer vision, in visual information processing systems. A comprehensive analysis of neural network approaches to solving computer vision problems is carried out, including systematization of key types of problems: image classification, object detection and semantic segmentation. The architectural principles of convolutional neural networks are ...
Added: September 10, 2026
Модель глубокого обучения для автоматизированной интерпретации медицинских электрофизиологических данных
Lebedev O. B., Шмелева А. Г., Гежа Н. С., Информатика и автоматизация (Труды СПИИРАН) 2026 Т. 25 № 3 С. 720–750
This paper describes the development of a neural network model for automated analysis of medical data in electrophysiology based on deep learning methods. The relevance of this work stems from the growing need to improve the objectivity, speed, and accuracy of processing complex spatiotemporal signals, such as ECG or EEG. Convolutional neural networks (CNNs), which ...
Added: September 10, 2026
Automated detection of wolf howls using audio spectrogram transformers
Makarov N., Savchenko A., Zemtsova I. et al., Scientific Reports 2025 Vol. 15 Article 26641
The grey wolf (Canis lupus) is a pivotal species for ecological studies. As a key participant in ecosystem processes, it also serves as a model for investigating social structure formation and ecological adaptation. However, the species’ complex social behavior, spatial dynamics, and expansive habitats make monitoring and population assessments across large areas particularly challenging. In recent years, audio traps ...
Added: June 16, 2026
Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening
Vasilev R., Savchenko A., Blinov P. et al., Frontiers in Medicine 2026 Vol. 13 Article 1778404
Automated disease screening systems face challenges when applied to multi-class medical image analysis, particularly under severe class imbalance inherent in clinical datasets. Retinal fundus imaging enables non-invasive screening for multiple ocular and systemic diseases simultaneously, yet current automated systems typically assess risk for only a single pathology or a limited disease range. We developed a ...
Added: June 16, 2026
Approaches to the Detection of Deepfake in the Financial Organization’s Activities
Belov A. V., Fedotov G., , in: Proceedings of the 2025 INTERNATIONAL CONFERENCE "QUALITY MANAGEMENT, DIGITAL SECURITY, INFORMATION TECHNOLOGIES" (2025 QM&DS&IT).: IEEE, 2025. Ch. 1 P. 3–7.
In recent years, significant progress has been observed as content generated using AI technologies. In addition, tools regularly appear with which scammers can create a realistic fake content. Deepfake detection methods are currently actively used in the activities of financial organizations. With their help, a departments within financial organizations responsible for IT Security identify cases ...
Added: April 17, 2026
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit