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.
@article{arxiv.2212.08448,
title = {From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search},
author = {Hadar Shavit and Filip Jatelnicki and Pol Mor-Puigventós and Wojtek Kowalczyk},
journal= {arXiv preprint arXiv:2212.08448},
year = {2022}
}
Comments
Accepted at ICPRAM 2023 for a 20 minutes oral presentation