From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search

Hadar Shavit, Filip Jatelnicki, Pol Mor-Puigventós, Wojtek Kowalczyk

2023

Abstract

In this paper, we present a modified Xception architecture, the NEXcepTion network. Our network has significantly better performance than the original Xception, achieving top-1 accuracy of 81.5% on the ImageNet validation dataset (an improvement of 2.5%) as well as a 28% higher throughput. Another variant of our model, NEXcepTion-TP, reaches 81.8% top-1 accuracy, similar to ConvNeXt (82.1%), while having a 27% higher throughput. Our model is the result of applying improved training procedures and new design decisions combined with an application of Neural Architecture Search (NAS) on a smaller dataset. These findings call for revisiting older architectures and reassessing their potential when combined with the latest enhancements. Our code is available at https://github.com/hadarshavit/NEXcepTion.

Paper Citation

in Harvard Style

Shavit H., Jatelnicki F., Mor-Puigventós P. and Kowalczyk W. (2023). From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 229-236. DOI: 10.5220/0011623100003411

in Bibtex Style

@conference{icpram23,
author={Hadar Shavit and Filip Jatelnicki and Pol Mor-Puigventós and Wojtek Kowalczyk},
title={From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={229-236},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011623100003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
SN - 978-989-758-626-2
AU - Shavit H.
AU - Jatelnicki F.
AU - Mor-Puigventós P.
AU - Kowalczyk W.
PY - 2023
SP - 229
EP - 236
DO - 10.5220/0011623100003411