Generative flows with invertible attentions

• Main Authors: SUKTHANKER, Rhea Sanjay, HUANG, Zhiwu, KUMAR, Suryansh, TIMOFTE, Radu, VAN GOOL, Luc
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: flow-based generative models; invertible attention; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/7612; https://ink.library.smu.edu.sg/context/sis_research/article/8615/viewcontent/01_Generative_Flows_With_Invertible_Attentions_CVPR_2022_paper.pdf
• Institution: Singapore Management University

Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while it has made breakthroughs in other domains. To fill the gap...