DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability

• URL: http://arxiv.org/abs/2308.09306v1
• Date: Fri, 18 Aug 2023 05:03:48 GMT
• Title: DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability
• Authors: Runhui Huang, Jianhua Han, Guansong Lu, Xiaodan Liang, Yihan Zeng, Wei Zhang, Hang Xu
• Abstract summary: We propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. We show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks.
• Score: 75.9781362556431
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for various downstream tasks by learning to align vision and language embeddings. In this paper, we explore the possibility of jointly modeling generation and discrimination. Specifically, we propose DiffDis to unify the cross-modal generative and discriminative pretraining into one single framework under the diffusion process. DiffDis first formulates the image-text discriminative problem as a generative diffusion process of the text embedding from the text encoder conditioned on the image. Then, we propose a novel dual-stream network architecture, which fuses the noisy text embedding with the knowledge of latent images from different scales for image-text discriminative learning. Moreover, the generative and discriminative tasks can efficiently share the image-branch network structure in the multi-modality model. Benefiting from diffusion-based unified training, DiffDis achieves both better generation ability and cross-modal semantic alignment in one architecture. Experimental results show that DiffDis outperforms single-task models on both the image generation and the image-text discriminative tasks, e.g., 1.65% improvement on average accuracy of zero-shot classification over 12 datasets and 2.42 improvement on FID of zero-shot image synthesis.

Related papers

• Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers [120.49126407479717]
  This paper explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketches and photos.
  arXiv  Detail & Related papers  (2024-03-12T00:02:03Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners [88.07317175639226]
  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.
  arXiv  Detail & Related papers  (2023-05-18T05:41:36Z)
• Your Diffusion Model is Secretly a Zero-Shot Classifier [90.40799216880342]
  We show that density estimates from large-scale text-to-image diffusion models can be leveraged to perform zero-shot classification. Our generative approach to classification attains strong results on a variety of benchmarks. Our results are a step toward using generative over discriminative models for downstream tasks.
  arXiv  Detail & Related papers  (2023-03-28T17:59:56Z)
• SinDiffusion: Learning a Diffusion Model from a Single Natural Image [159.4285444680301]
  We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. It is based on two core designs. First, SinDiffusion is trained with a single model at a single scale instead of multiple models with progressive growing of scales. Second, we identify that a patch-level receptive field of the diffusion network is crucial and effective for capturing the image's patch statistics.
  arXiv  Detail & Related papers  (2022-11-22T18:00:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.