Published June 5, 2026 | Version v1
Image Open

Visualizations of the Resuts of Classification of ImageNet Validation Set Before and After Compression by DAC and PDCTC

Authors/Creators

  • 1. ROR icon National Aerospace University – Kharkiv Aviation Institute

Description

This repository contains visualizations of the results of the classification of ImageNet validation set (50,000 images, 1,000 classes) by 28 pre-trained CNNs before and after compression by Discrete Atomic Compression (DAC) and a Progressive DCT-based Coder (PDCTC).

References

  • Discrete Atomic Compression: Makarichev, V.; Vasilyeva, I.; Lukin, V.; Vozel, B.; Shelestov, A.; Kussul, N. Discrete Atomic Transform-Based Lossy Compression of Three-Channel Remote Sensing Images with Quality Control. Remote Sens. 2022, 14, 125. DOI: https://doi.org/10.3390/rs14010125.
  • Progressive DCT-based Coder: Makarichev, V.; Lukin, V.; Brysina, I. Progressive DCT-Based Coder and Its Comparison to Atomic Function Based Image Lossy Compression. In Proceedings of the 2022 IEEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), Lviv-Slavske, Ukraine, 22-26 February 2022; pp. 1-6. DOI: https://doi.org/10.1109/TCSET55632.2022.9766871.
  • ImageNet: Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; Berg, A.C.; Fei-Fei, L. ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. 2015, 115, pp. 211--252. DOI: https://doi.org/10.1007/s11263-015-0816-y.

Files

figures.zip

Files (1.3 MB)

Name Size Download all
md5:4f8aab0fb99b8576134c1ab2a87b751f
1.3 MB Preview Download

Additional details

References

  • Makarichev, V.; Vasilyeva, I.; Lukin, V.; Vozel, B.; Shelestov, A.; Kussul, N. Discrete Atomic Transform-Based Lossy Compression of Three-Channel Remote Sensing Images with Quality Control. Remote Sens. 2022, 14, 125. DOI: https://doi.org/10.3390/rs14010125.
  • Makarichev, V.; Lukin, V.; Brysina, I. Progressive DCT-Based Coder and Its Comparison to Atomic Function Based Image Lossy Compression. In Proceedings of the 2022 IEEE 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET), Lviv-Slavske, Ukraine, 22-26 February 2022; pp. 1-6. DOI: https://doi.org/10.1109/TCSET55632.2022.9766871.
  • Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; Berg, A.C.; Fei-Fei, L. ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. 2015, 115, pp. 211--252. DOI: https://doi.org/10.1007/s11263-015-0816-y.