BriefGPT.xyz
Jul, 2024
探索基于短语分时的文本至图像扩散模型
Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model
HTML
PDF
Danni Yang, Ruohan Dong, Jiayi Ji, Yiwei Ma, Haowei Wang...
TL;DR
通过扩展扩散模型的架构,本研究提出了一种使用提问学习的方法,实现了基于句子构建的图像理解,进而在零样例的情况下实现了上下文感知的短语级理解,证明了扩散模型在语境感知的短语级理解方面的能力。
Abstract
Recently,
diffusion models
have increasingly demonstrated their capabilities in vision understanding. By leveraging
prompt-based learning
to construct sentences, these models have shown proficiency in classificat
→