Xception is an extension of Inception, introduced in Xception: Deep Learning with Depthwise Separable Convolutions, François Chollet, 2016, https://arxiv.org/abs/1610.02357 . Xception uses a new concept called depthwise separable convolution operation which allows it to outperform Inception-v3 on a large 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.