CapsuleGAN: Generative Adversarial Capsule Network
By Ayush Jaiswal, Wael AbdAlmageed, Premkumar Natarajan. 2018
169 citations recorded by the source corpus.
We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adversarial network (GAN) setting, while modeling image data. We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates the CapsNet margin loss, for training CapsuleGAN models. We show that CapsuleGAN outperforms convolutional-GAN at modeling image data distribution on the MNIST dataset of handwritten digits, evaluated on the generative adversarial metric and at semi-supervised image classification.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yee Whye Teh
- Geoffrey E. Hinton
- Ruslan Salakhutdinov
- Yoshua Bengio
- Sara Sabour
- Adam R. Kosiorek
- Sergey Levine
- Michael I. Jordan
In Computer Vision and Pattern Recognition
- Geoffrey E. Hinton
- Yee Whye Teh
- Luc Van Gool
- Sara Sabour
- Dacheng Tao
- Xiaogang Wang
- Jitendra Malik
- Trevor Darrell
Citations in the corpus
- Stacked Capsule Autoencoders (2019, methodology): “We used sobel-filtered images as the reconstruction target for SVHN and CIFAR 10, as in Jaiswal et al., 2018, while using the raw pixel intensities as the input to PCAE .”
- 3D Point Capsule Networks (2018, unknown): “[14], Saqur et al .”
- PF-Net: Point Fractal Network for 3D Point Cloud Completion (2020, background): “3D point capsule networks [23, 36, 12, 26] surpasses the performance of other methods and becomes the state-of-the-art Auto-Encoder processing point cloud, especially in the domain of point cloud reconstruction.”
- Generative Adversarial Networks (GANs) (2020, background): “Jaiswal et al. [64] introduced a change in D’s architecture and argued to use a capsule networks (CapsNets) ACM Computing Surveys, Vol. 54, No. 3, Article 63.”