AI-GAN: signal de-interference via asynchronous interactive generative adversarial network

Jin, Xin, Chen, Zhibo, Lin, Jianxin, Zhou, Wei, Chen, Jiale and Shan, Chaowei 2019. AI-GAN: signal de-interference via asynchronous interactive generative adversarial network. Presented at: 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), Shanghai, 08-12 July 2019. 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 10.1109/ICMEW.2019.00046

Full text not available from this repository.

Abstract

Interfering signals, such as rain streak, haze, noise, etc, introduce various types of visibility degradation on original clean signals. Traditional algorithms tackle the signal de-interference problem by the way of signal removal, which usually causes over-smoothness and unexpected artifacts. Hereby, this paper attempts to solve this problem from a totally different perspective of signal decomposition, and introduces the interaction and constraints between the two decomposed signals during the restoration procedure. Specifically, we propose an Asynchronous Interactive Generative Adversarial Network (AI-GAN), which decomposes the degraded signal into original and interfering parts progressively through a double branch structure. Each branch employs an asynchronous synthesis strategy for the corresponding generator and interacts with each other by exchanging the feed-forward signal values and sharing the corresponding feedback gradients, achieving an effect of mutual adversarial optimization. The proposed AI-GAN shows significant qualitative and quantitative improvement on general signal de-interference tasks such as deraining, dehazing, and denoising.

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	IEEE
ISBN:	978-1-5386-9215-8
Last Modified:	21 Sep 2023 14:00
URI:	https://orca.cardiff.ac.uk/id/eprint/162069

Actions (repository staff only)

Edit Item