2021/08/14 by Dina Tantawy, Tantawy, Dina, Mohamed Zahran +4 · 1 citation
Computer Science · #Acceleration #Advanced Image Processing Techniques #Algorithm #Artificial intelligence #Compression (physics) #Computation #Computer Vision and Pattern Recognition (cs.CV) #Computer engineering #Computer science #Data flow diagram #Deep learning #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Generative grammar #Machine Learning (cs.LG) #Machine learning #Neural and Evolutionary Computing (cs.NE) #Quality (philosophy) #Theoretical computer science #Transfer of learning #cs.CV #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.2108.06626
published in arXiv (Cornell University) (Cornell University) · 21 pages, 17 figures
arxiv created 2021/08/14 · openalex publication_date 2021/08/14 · arxiv updated 2021/08/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Since its invention, Generative adversarial networks (GANs) have shown outstanding results in many applications. Generative Adversarial Networks are powerful yet, resource-hungry deep-learning models. Their main difference from ordinary deep learning models is the nature of their output. For example, GAN output can be a whole image versus other models detecting objects or classifying images. Thus, the architecture and numeric precision of the network affect the quality and speed of the solution. Hence, accelerating GANs is pivotal. Accelerating GANs can be classified into three main tracks: (1) Memory compression, (2) Computation optimization, and (3) Data-flow optimization. Because data transfer is the main source of energy usage, memory compression leads to the most savings. Thus, in this paper, we survey memory compression techniques for CNN-Based GANs. Additionally, the paper summarizes opportunities and challenges in GANs acceleration and suggests open research problems to be further investigated.