paper-with-me

Papers

CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning

2022-10-10 · Shitong Xu

Image captioning task has been extensively researched by previous work. However, limited experiments focus on generating captions based on non-autoregressive text decoder. Inspired by the recent success of the denoising diffusion model on image synthesis tasks, we apply denoising diffusion probabilistic models to text generation in image captioning tasks. We show that our CLIP-Diffusion-LM is capable of generating image captions using significantly fewer inference steps than autoregressive models. On the Flickr8k dataset, the model achieves 0.1876 BLEU-4 score. By training on the combined Flickr8k and Flickr30k dataset, our model achieves 0.2470 BLEU-4 score. Our code is available at https://github.com/xu-shitong/diffusion-image-captioning.

📄 PDF Abstract BibTeX arXiv:2210.04559

Code (1)

xu-shitong/diffusion-image-captioning 공식 구현 pytorch

Tasks

DecoderDenoisingImage CaptioningImage GenerationText Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity

2023-08-14 · Weijian Mai, Zhijun Zhang

Image reconstruction and captioning from brain activity evoked by visual stimuli allow researchers to further understand the connection between the human brain and the visual perception system. While deep generative mode…

AllBrain DecodingImage CaptioningImage Reconstruction

DiffCap: Exploring Continuous Diffusion on Image Captioning

2023-05-20 · Yufeng He, Zefan Cai, Xu Gan, Baobao Chang

Current image captioning works usually focus on generating descriptions in an autoregressive manner. However, there are limited works that focus on generating descriptions non-autoregressively, which brings more decoding…

Caption GenerationDiversityImage CaptioningImage Description+2

Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image Captioning

2025-01-01 · CVPR 2025 1 · Jeong Ryong Lee, Yejee Shin, Geonhui Son, Dosik Hwang

The modality gap between vision and text embeddings in CLIP presents a significant challenge for zero-shot image captioning, limiting effective cross-modal representation. Traditional approaches, such as noise inject…

cross-modal alignmentDenoisingImage Captioning

Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning

2023-09-10 · Guisheng Liu, Yi Li, Zhengcong Fei, Haiyan Fu 외

While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems. In th…

DenoisingDiversityImage Captioning

clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP

2022-10-05 · Justin N. M. Pinkney, Chuan Li

We introduce a new method to efficiently create text-to-image models from a pre-trained CLIP and StyleGAN. It enables text driven sampling with an existing generative model without any external data or fine-tuning. This …

Denoising