RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation

Vision-language representation learning models (e.g., CLIP) have achieved state-of-the-art performance on various downstream tasks, which usually need large-scale training data to learn discriminative representation. Recent progress on generative diffusion models (e.g., DALL-E 2) has demonstrated that diverse high-quality samples can be synthesized by randomly sampling from generative distribution. By virtue of generative capability in this paper, we propose a novel visionlanguage Representation Learning method with diffusion-based Embedding Generation (RLEG), which exploits diffusion models to generate feature embedding online for learning effective vision-language representation. Specifically, we first adopt image and text encoders to extract the corresponding embeddings. Secondly, pretrained diffusion-based embedding generators are harnessed to transfer the embedding modality online between vision and language domains. The embeddings generated from the generators are then served as augmented embedding-level samples, which are applied to contrastive learning with the variant of the CLIP framework. Experimental results show that the proposed method could learn effective representation and achieve state-of-theart performance on various tasks including image classification, image-text retrieval, object detection, semantic segmentation, and text-conditional image generation.