LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?
Yuchi WangShuhuai RenRundong GaoLinli YaoQingyan GuoKaikai AnJianhong BaiXu SunPublished in: CoRR (2024)
Keyphrases
- autoregressive
- gaussian markov random field
- random fields
- image data
- multiscale
- text generation
- input image
- diffusion models
- image segmentation
- edge detection
- high resolution
- natural language generation
- image analysis
- segmentation method
- diffusion model
- natural images
- hidden markov models
- anisotropic diffusion
- recommender systems
- computer vision