CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cao, Qingqing, Najibi, Mahyar, Mehta, Sachin
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.11963