This paper creates a publicly available framework (Open Vision Banana) to turn pre-trained image generators into general-purpose vision systems that can understand and perceive real-world images. Practitioners can use this framework to improve their own vision tasks by adapting and fine-tuning the pre-trained models.
Firehose
Filtered to Papers, tagged “perception” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives