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

Shranjeno v:

Bibliografske podrobnosti
izdano v:	arXiv.org (Dec 2, 2024), p. n/a
Glavni avtor:	Li, You
Drugi avtorji:	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 dostop:	Citation/Abstract Full text outside of ProQuest
Oznake:	Označite Brez oznak, prvi označite!

Komentirajte kot prvi!