Transcription of Generative Adversarial Transformers
{{id}} {{{paragraph}}}
Generative Adversarial TransformersDrew A. Hudson Department of Computer ScienceStanford Lawrence ZitnickFacebook AI ResearchFacebook, introduce the GANformer, a novel and effi-cient type of transformer, and explore it for thetask of visual Generative modeling. The networkemploys a bipartite structure that enables long-range interactions across the image, while main-taining computation of linear efficiency, that canreadily scale to high-resolution synthesis. It itera-tively propagates information from a set of latentvariables to the evolving visual features and viceversa, to support the refinement of each in light ofthe other, and encourage the emergence of compo-sitional representations for objects and scenes. Incontrast to the classic transformer architecture, itutilizes multiplicative integration that allows flexi-ble region-based modulation, and can thus be seenas a multi-latent generalization of the successfulStyleGAN network.
slots, but are mostly applied in the contexts of synthetic and oftentimes fairly rudimentary 2D settings. Works such as Capsule networks [29, 60] leverage ideas from psychology about Gestalt principles [34, 62], perceptual grouping [6] or analysis-by-synthesis [4], and like us, introduce ways to piece together visual elements to discover compound
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}