TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Image Classification	<h2>oi</h2>	NEXcepTion-S	Top 1 Accuracy	82%	# 531
Image Classification	<h2>oi</h2>	NEXcepTion-T	Top 1 Accuracy	81.5%	# 578
Image Classification	<h2>oi</h2>	NEXcepTion-TP	Top 1 Accuracy	81.8%	# 554

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/from-xception-to-nexception-new-design/image-classification-on-imagenet)](https://paperswithcode.com/sota/image-classification-on-imagenet?p=from-xception-to-nexception-new-design)`

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

16 Dec 2022 · 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.

PDF Abstract

Code

Add Remove Mark official

hadarshavit/nexception official

Tasks

Add Remove

Image Classification

Neural Architecture Search

Datasets

CIFAR-100

ImageNet-R

ImageNet-A

ImageNet-Sketch

Results from the Paper

Edit

Ranked #531 on Image Classification on <h2>oi</h2>

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Image Classification	<h2>oi</h2>	NEXcepTion-S	Top 1 Accuracy	82%	# 531	Compare
Image Classification	<h2>oi</h2>	NEXcepTion-T	Top 1 Accuracy	81.5%	# 578	Compare
Image Classification	<h2>oi</h2>	NEXcepTion-TP	Top 1 Accuracy	81.8%	# 554	Compare

Methods

Add Remove

1x1 Convolution • Adam • Average Pooling • ConvNeXt • Convolution • Dense Connections • Depthwise Convolution • Depthwise Separable Convolution • Global Average Pooling • LAMB • Max Pooling • Pointwise Convolution • RandAugment • ReLU • Residual Connection • Softmax • Xception

Edit Social Preview

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

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove