Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Samiei, Mohammadmahdi"'
Autor:
Abdollah, Ali, Izadi, Amirmohammad, Saghafian, Armin, Vahidimajd, Reza, Mozafari, Mohammad, Mirzaei, Amirreza, Samiei, Mohammadmahdi, Baghshah, Mahdieh Soleymani
Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss between the glo
Externí odkaz:
http://arxiv.org/abs/2409.08206