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

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

16 Dec 2022arXiv:2212.08448archive 2025-07-28

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

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.

PaperPDFCode

Code

hadarshavit/nexception officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet NEXcepTion-S Top 1 Accuracy 82% #581 of 1060 Archive leaderboard report
Image Classification ImageNet NEXcepTion-TP Top 1 Accuracy 81.8% #607 of 1060 Archive leaderboard report
Image Classification ImageNet NEXcepTion-T Top 1 Accuracy 81.5% #631 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAdamAverage PoolingConvNeXtConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionGlobal Average PoolingLAMBMax PoolingPointwise ConvolutionRandAugmentResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections