Convolutional Neural Network Compression Based on Improved Fractal Decomposition Algorithm for Large Scale Optimization

Simple item page
dc.contributor.authorLlanza, Arcadi
dc.contributor.authorKeddous, Fekhr Eddine
dc.contributor.authorShvai, Nadiya
dc.contributor.authorNakib, Amir
dc.date.accessioned2024-09-13T05:29:13Z
dc.date.available2024-09-13T05:29:13Z
dc.date.issued2023
dc.description.abstractDeep learning based methods have become the de-facto standard for various computer vision tasks. Nevertheless, they have repeatedly shown their vulnerability to various form of input perturbations such as pixels modification, region anonymization, etc. which are closely related to the adversarial attacks. This research particularly addresses the case of image anonymization, which is significantly important to preserve privacy and hence to secure digitized form of personal information from being exposed and potentially misused by different services that have captured it for various purposes. However, applying anonymization causes the classifier to provide different class decisions before and after applying it and therefore reduces the classifier’s reliability and usability. In order to achieve a robust solution to this problem we propose a novel anonymization procedure that allows the existing classifiers to become class decision invariant on the anonymized images without any modification requires to apply on the classification models. We conduct numerous experiments on the popular ImageNet benchmark as well as on a large scale industrial toll classification problem’s dataset. Obtained results confirm the efficiency and effectiveness of the proposed method as it obtained 0% rate of class decision change for both datasets compared to 15.95% on ImageNet and 0.18% on toll dataset obtained by applying the na¨ıve anonymization approaches. Moreover, it has shown a great potential to be applied to similar problems from different domains.en_US
dc.identifier.citationConvolutional Neural Network Compression Based on Improved Fractal Decomposition Algorithm for Large Scale Optimization / Arcadi Llanza, Fekhr Eddine Keddous, Nadiya Shvai, Amir Nakib // IEEE International Conference on Systems, Man, and Cybernetics (SMC), Honolulu, Oahu, HI, USA. - 2023. - P. 5084-5089. - https://doi.org/10.1109/SMC53992.2023.10394477en_US
dc.identifier.urihttps://doi.org/10.1109/SMC53992.2023.10394477
dc.identifier.urihttps://ekmair.ukma.edu.ua/handle/123456789/31543
dc.language.isoenen_US
dc.relation.sourceIEEE International Conference on Systems, Man, and Cybernetics (SMC), Honolulu, Oahu, HI, USA.en_US
dc.statusfirst publisheduk_UA
dc.subjectimage anonymizationen_US
dc.subjectpersonal informationen_US
dc.subjectanonymized imagesen_US
dc.subjectdeep learning modelsen_US
dc.subjectconference materialsen_US
dc.titleConvolutional Neural Network Compression Based on Improved Fractal Decomposition Algorithm for Large Scale Optimizationen_US
dc.typeConference materialsuk_UA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Shvai_Adaptive_Image_Anonymization_in_the_Context_of_Image_Classification_with_ICCV_2023_paper.pdf
Size:
6.73 MB
Format:
Adobe Portable Document Format
Download
Collections
Кафедра математики