CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Krestenitis, Marios, Tzelepis, Christos, Ioannidis, Konstantinos, Vrochidis, Stefanos, Kompatsiaris, Ioannis, Tzimiropoulos, Georgios, Gong, Shaogang, Patras, Ioannis
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.18282