Text-to-Image Diffusion Models are Zero-Shot Classifiers

Kevin Clark, Priyank Jaini

Keywords: diffusion models, zero-shot, text-to-image, generative models, foundation models

Abstract:

The excellent generative capabilities of text-to-image diffusion models suggest they learn informative representations of image-text data.
However, what knowledge their representations capture is not fully understood, and they have not been thoroughly explored on downstream tasks.
We investigate diffusion models by proposing a method for evaluating them as zero-shot classifiers.
The key idea is using a diffusion model's ability to denoise a noised image given a text description of a label as a proxy for that label's likelihood.
We apply our method to Imagen, using it to probe fine-grained aspects of Imagen's knowledge and comparing it with CLIP's zero-shot abilities.
Imagen performs competitively with CLIP on a wide range of zero-shot image classification datasets.
Additionally, it achieves state-of-the-art results on shape/texture bias tests and can successfully perform attribute binding while CLIP cannot.
Although generative pre-training is prevalent in NLP, visual foundation models often use other methods such as contrastive learning.
Based on our findings, we argue that generative pre-training should be explored as a compelling alternative for vision and vision-language problems.