ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements

Bibliografske podrobnosti

izdano v:	arXiv.org (Nov 18, 2024), p. n/a
Glavni avtor:	Aydın, M Arda
Drugi avtorji:	Efe Mert Çırpar, Abdinli, Elvin, Unal, Gozde, Sahin, Yusuf H
Izdano:	Cornell University Library, arXiv.org
Teme:	Data augmentation Computer vision Semantic segmentation Large language models Image enhancement Image segmentation Pascal (programming language)
Online dostop:	Citation/Abstract Full text outside of ProQuest
Oznake:	Označite Brez oznak, prvi označite!