Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners

TL;DR

This paper introduces Discriminative Stable Diffusion (DSD), a method that repurposes pre-trained diffusion models for few-shot image-text matching by leveraging cross-attention scores and prompt learning, achieving superior results.

Contribution

The paper presents a novel approach to convert pre-trained diffusion models into discriminative learners for image-text matching, a task not traditionally associated with diffusion models.

Findings

DSD outperforms state-of-the-art methods on benchmark datasets.

Cross-attention scores effectively capture visual-textual mutual influence.

Efficient prompt learning enables few-shot discriminative performance.

Abstract

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified in text prompts, can we leverage the powerful representations learned by pre-trained diffusion models for discriminative tasks such as image-text matching? To answer this question, we propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainly uses the cross-attention score of a Stable Diffusion model to capture the mutual influence between visual and textual information and fine-tune the model via efficient attention-based prompt learning to perform image-text matching. By comparing DSD with state-of-the-art methods on several benchmark datasets, we demonstrate the potential of using pre-trained diffusion models for discriminative tasks with superior results on few-shot image-text matching.