Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟬𝟵 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Researchers Propose ‘𝗣𝗿𝗼𝗷𝗲𝗰𝘁𝗲𝗱-𝗚𝗔𝗡𝘀’, To Improve Image Quality, Sample Efficiency, And Convergence Speed Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 𝗣𝗮𝗽𝗲𝗿: Projected GANs Converge Faster. 🔸 This paper is published by NeurIPS 2021. 🔸 Researchers from the University of Tübingen, Max Planck Institute for Intelligent Systems, and Heidelberg have studied ways to improve GAN training by using pre-trained representations. The researchers proposed a more effective strategy (Projected-GAN) that combines features across channels and resolutions. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. 🔸We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. 🔸 Our Projected GAN improves image quality, sample efficiency, and convergence speed. It is further compatible with resolutions of up to one Megapixel and advances the state-of-the-art Fréchet Inception Distance (FID) on twenty-two benchmark datasets. Importantly, Projected GANs match the previously lowest FIDs up to 40 times faster, cutting the wall-clock time from 5 days to less than 3 hours given the same computational resources. #computervision #machinelearning #data