AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks

Spremljeno u:

Bibliografski detalji
Izdano u:	arXiv.org (Dec 2, 2024), p. n/a
Glavni autor:	Li, You
Daljnji autori:	Fan, Ma, Yang, Yi
Izdano:	Cornell University Library, arXiv.org
Teme:	Large language models Image segmentation Image retrieval Retrieval Image annotation Perception Layouts Controllability Instance segmentation Modules Image quality Object recognition Image processing Data collection Synthetic data
Online pristup:	Citation/Abstract Full text outside of ProQuest
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!

Budi prvi tko komentira!