all AI news
Google’s MaskGIT Outperforms SOTA Transformer Models on Conditional Image Generation and Accelerates Autoregressive Decoding by up to 64x
Feb. 14, 2022, 4:05 p.m. | Synced
Synced syncedreview.com
A Google Research team proposes Masked Generative Image Transformer (MaskGIT), a novel image synthesis paradigm that uses a bidirectional transformer decoder. MaskGIT significantly outperforms state-of-the-art transformer models on the ImageNet dataset and accelerates autoregressive decoding by up to 64x.
The post Google’s MaskGIT Outperforms SOTA Transformer Models on Conditional Image Generation and Accelerates Autoregressive Decoding by up to 64x first appeared on Synced.
ai artificial intelligence autoregressive models computer vision & graphics google image image generation machine learning machine learning & data science ml research sota technology transformer transformers
More from syncedreview.com / Synced
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne