Xception: Deep Learning with Depthwise Separable Convolutions

Code

• github.com/tensorflow/models
  tf★ 77,694
• github.com/rwightman/pytorch-image-models
  pytorch★ 36,538
• github.com/PaddlePaddle/PaddleClas
  paddle★ 5,788
• github.com/osmr/imgclsmob
  mxnet★ 3,015
• github.com/DarshanDeshpande/jax-models
  jax★ 161
• github.com/IMvision12/keras-vision-models
  pytorch★ 8
• github.com/drscotthawley/SPNet
  tf★ 2
• github.com/bluejurand/Photos-colorization
  tf★ 0
• github.com/alililia/ms_contrib/tree/main/gpu_xception
  mindspore★ 0
• github.com/crowdAI/crowdai-musical-genre-recognition-starter-kit
  none★ 0

Abstract

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset (which Inception V3 was designed for), and significantly outperforms Inception V3 on a larger image classification dataset comprising 350 million images and 17,000 classes. Since the Xception architecture has the same number of parameters as Inception V3, the performance gains are not due to increased capacity but rather to a more efficient use of model parameters.

Tasks

Benchmark Results

Reproductions