SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

SimVLM: Simple Visual Language Model Pretraining with Weak Supervision

https://arxiv.org/abs/2108.10904

May 10, 2023

Multimodal Pretraining, Vision-Language Pretraining, Zero-shot Learning, Vision and Language,

ICLR (2022)

概要

新規性・差分

アイデア

結果

一覧へ戻る