Diffusion Guided Domain Adaptation of Image Generators

• URL: http://arxiv.org/abs/2212.04473v2
• Date: Fri, 9 Dec 2022 08:58:13 GMT
• Title: Diffusion Guided Domain Adaptation of Image Generators
• Authors: Kunpeng Song, Ligong Han, Bingchen Liu, Dimitris Metaxas, Ahmed Elgammal
• Abstract summary: We show that the classifier-free guidance can be leveraged as a critic and enable generators to distill knowledge from large-scale text-to-image diffusion models. Generators can be efficiently shifted into new domains indicated by text prompts without access to groundtruth samples from target domains. Although not trained to minimize CLIP loss, our model achieves equally high CLIP scores and significantly lower FID than prior work on short prompts.
• Score: 22.444668833151677
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain? In this paper, we show that the classifier-free guidance can be leveraged as a critic and enable generators to distill knowledge from large-scale text-to-image diffusion models. Generators can be efficiently shifted into new domains indicated by text prompts without access to groundtruth samples from target domains. We demonstrate the effectiveness and controllability of our method through extensive experiments. Although not trained to minimize CLIP loss, our model achieves equally high CLIP scores and significantly lower FID than prior work on short prompts, and outperforms the baseline qualitatively and quantitatively on long and complicated prompts. To our best knowledge, the proposed method is the first attempt at incorporating large-scale pre-trained diffusion models and distillation sampling for text-driven image generator domain adaptation and gives a quality previously beyond possible. Moreover, we extend our work to 3D-aware style-based generators and DreamBooth guidance.

Related papers

• E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation [69.72194342962615]
  We introduce and address a novel research direction: can the process of distilling GANs from diffusion models be made significantly more efficient? First, we construct a base GAN model with generalized features, adaptable to different concepts through fine-tuning, eliminating the need for training from scratch. Second, we identify crucial layers within the base GAN model and employ Low-Rank Adaptation (LoRA) with a simple yet effective rank search process, rather than fine-tuning the entire base model. Third, we investigate the minimal amount of data necessary for fine-tuning, further reducing the overall training time.
  arXiv  Detail & Related papers  (2024-01-11T18:59:14Z)
• Elucidating The Design Space of Classifier-Guided Diffusion Generation [17.704873767509557]
  We show that it is possible to achieve significant performance improvements over existing guidance schemes by leveraging off-the-shelf classifiers in a training-free fashion. Our proposed approach has great potential and can be readily scaled up to text-to-image generation tasks.
  arXiv  Detail & Related papers  (2023-10-17T14:34:58Z)
• DiffDis: Empowering Generative Diffusion Model with Cross-Modal Discrimination Capability [75.9781362556431]
  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.
  arXiv  Detail & Related papers  (2023-08-18T05:03:48Z)
• 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)
• Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks [54.80435295622583]
  One-shot generative domain adaption aims to transfer a pre-trained generator on one domain to a new domain using one reference image only. We present a novel one-shot generative domain adaption method, i.e., DiFa, for diverse generation and faithful adaptation.
  arXiv  Detail & Related papers  (2022-07-18T16:29:41Z)
• D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation [17.20913584422917]
  Few-shot image generation aims at generating realistic images through training a GAN model given few samples. A typical solution for few-shot generation is to transfer a well-trained GAN model from a data-rich source domain to the data-deficient target domain. We propose a novel self-supervised transfer scheme termed D3T-GAN, addressing the cross-domain GANs transfer in few-shot image generation.
  arXiv  Detail & Related papers  (2022-05-12T11:32:39Z)
• StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators [63.85888518950824]
  We present a text-driven method that allows shifting a generative model to new domains. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains.
  arXiv  Detail & Related papers  (2021-08-02T14:46:46Z)
• On Leveraging Pretrained GANs for Generation with Limited Data [83.32972353800633]
  generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in a training dataset, suggesting potential for augmenting training sets with GAN-generated data. We leverage existing GAN models pretrained on large-scale datasets to introduce additional knowledge, following the concept of transfer learning. An extensive set of experiments is presented to demonstrate the effectiveness of the proposed techniques on generation with limited data.
  arXiv  Detail & Related papers  (2020-02-26T21:53:36Z)

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.