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.
Keywords
Convolution (computer science)PointwiseSeparable spaceConvolutional neural networkComputer scienceArtificial intelligenceDeep learningInterpretation (philosophy)Pattern recognition (psychology)Image (mathematics)AlgorithmArtificial neural networkMathematicsMathematical analysis
Affiliated Institutions
Related Publications
Xception: Deep Learning with Depthwise Separable Convolutions
We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convo...
Interleaved Group Convolutions
In this paper, we present a simple and modularized neural network architecture, named interleaved group convolutional neural networks (IGCNets). The main point lies in a novel b...
Active Convolution: Learning the Shape of Convolution for Image Classification
In recent years, deep learning has achieved great success in many computer vision applications. Convolutional neural networks (CNNs) have lately emerged as a major approach to i...
Adding Conditional Control to Text-to-Image Diffusion Models
We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-re...
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Sca...
Publication Info
- Year
- 2017
- Type
- article
- Pages
- 1800-1807
- Citations
- 17644
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
17644
OpenAlex
Cite This
François Chollet
(2017).
Xception: Deep Learning with Depthwise Separable Convolutions.
, 1800-1807.
https://doi.org/10.1109/cvpr.2017.195
Identifiers
- DOI
- 10.1109/cvpr.2017.195