Distilling portable Generative Adversarial Networks for Image Translation

By Hanting Chen, Yunhe Wang, Han Shu, Changyuan Wen, Chunjing Xu, Boxin Shi, Chao Xu, Chang Xu. 2020

89 citations recorded by the source corpus.

Despite Generative Adversarial Networks (GANs) have been widely used in various image-to-image translation tasks, they can be hardly applied on mobile devices due to their heavy computation and storage cost. Traditional network compression methods focus on visually recognition tasks, but never deal with generation tasks. Inspired by knowledge distillation, a student generator of fewer parameters is trained by inheriting the low-level and high-level information from the original heavy teacher generator. To promote the capability of student generator, we include a student discriminator to measure the distances between real images, and images generated by student and teacher generators. An adversarial learning process is therefore established to optimize student generator and student discriminator. Qualitative and quantitative analysis by conducting experiments on benchmark datasets demonstrate that the proposed method can learn portable generative models with strong performance.

Subfields: Cancer Research, 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 Computer Vision and Pattern Recognition

1. Zhangyang Wang
2. Shiyu Chang
3. Yingxue Pang
4. Tao Qin
5. Zhibo Chen
6. Jianxin Lin
7. Chunhua Shen
8. Tie-Yan Liu

Citations in the corpus

• Adversarially Robust Neural Architectures (2020, unknown): “D EEP neural networks have shown remarkable performance in various applications, such as image classification [1], [2], [3], object detection [4], and machine translation [5], [6].”
• TransGAN: Two Transformers Can Make One Strong GAN (2021, background): “Its popularity among computer vision tasks rises recently (Parmar et al., 2018; Yang et al., 2020; Zeng et al., 2020; Carion et al., 2020; Wu et al., 2020; Chen et al., 2020a).”
• Image-to-Image Translation: Methods and Applications (2021, methodology): “Semantic synthesis [113], [1], [87], [114], [3], [4], [117], [118] [15] [102], [2], [131], [137], [146] [79], [153], [154] \ [112], [155] [168] \ \ \ \”