ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer

• URL: http://arxiv.org/abs/2403.13652v2
• Date: Wed, 25 Sep 2024 07:08:46 GMT
• Title: ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer
• Authors: Hiroki Azuma, Yusuke Matsui, Atsuto Maki,
• Abstract summary: This paper proposes a zero-shot domain adaptation method based on diffusion models, called ZoDi. First, we utilize an off-the-shelf diffusion model to synthesize target-like images by transferring the domain of source images to the target domain. Secondly, we train the model using both source images and synthesized images with the original representations to learn domain-robust representations.
• Score: 13.956618446530559
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep learning models achieve high accuracy in segmentation tasks among others, yet domain shift often degrades the models' performance, which can be critical in real-world scenarios where no target images are available. This paper proposes a zero-shot domain adaptation method based on diffusion models, called ZoDi, which is two-fold by the design: zero-shot image transfer and model adaptation. First, we utilize an off-the-shelf diffusion model to synthesize target-like images by transferring the domain of source images to the target domain. In this we specifically try to maintain the layout and content by utilising layout-to-image diffusion models with stochastic inversion. Secondly, we train the model using both source images and synthesized images with the original segmentation maps while maximizing the feature similarity of images from the two domains to learn domain-robust representations. Through experiments we show benefits of ZoDi in the task of image segmentation over state-of-the-art methods. It is also more applicable than existing CLIP-based methods because it assumes no specific backbone or models, and it enables to estimate the model's performance without target images by inspecting generated images. Our implementation will be publicly available.

Related papers

• Hybrid diffusion models: combining supervised and generative pretraining for label-efficient fine-tuning of segmentation models [55.2480439325792]
  We propose a new pretext task, which is to perform simultaneously image denoising and mask prediction on the first domain. We show that fine-tuning a model pretrained using this approach leads to better results than fine-tuning a similar model trained using either supervised or unsupervised pretraining.
  arXiv  Detail & Related papers  (2024-08-06T20:19:06Z)
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models [56.71672127740099]
  We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets. We leverage different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation. Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets.
  arXiv  Detail & Related papers  (2024-03-29T10:38:25Z)
• Generating Reliable Pixel-Level Labels for Source Free Domain Adaptation [13.913151437401472]
  ReGEN comprises an image-to-image translation network and a segmentation network. Our workflow generates target-like images using the noisy predictions from the original target domain images.
  arXiv  Detail & Related papers  (2023-07-03T09:44:13Z)
• Domain Agnostic Image-to-image Translation using Low-Resolution Conditioning [6.470760375991825]
  We propose a domain-agnostic i2i method for fine-grained problems, where the domains are related. We present a novel approach that relies on training the generative model to produce images that both share distinctive information of the associated source image. We validate our method on the CelebA-HQ and AFHQ datasets by demonstrating improvements in terms of visual quality.
  arXiv  Detail & Related papers  (2023-05-08T19:58:49Z)
• One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models [15.590759602379517]
  Adapting a segmentation model from a labeled source domain to a target domain is one of the most challenging problems in domain adaptation. We leverage text-to-image diffusion models to generate a synthetic target dataset with photo-realistic images. Experiments show that our method surpasses the state-of-the-art OSUDA methods by up to +7.1%.
  arXiv  Detail & Related papers  (2023-03-31T14:16:38Z)
• Sketch-Guided Text-to-Image Diffusion Models [57.12095262189362]
  We introduce a universal approach to guide a pretrained text-to-image diffusion model. Our method does not require to train a dedicated model or a specialized encoder for the task. We take a particular focus on the sketch-to-image translation task, revealing a robust and expressive way to generate images.
  arXiv  Detail & Related papers  (2022-11-24T18:45:32Z)
• 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)
• Saliency-Driven Active Contour Model for Image Segmentation [2.8348950186890467]
  We propose a novel model that uses the advantages of a saliency map with local image information (LIF) and overcomes the drawbacks of previous models. The proposed model is driven by a saliency map of an image and the local image information to enhance the progress of the active contour models.
  arXiv  Detail & Related papers  (2022-05-23T06:02:52Z)
• Unsupervised Deep Learning Meets Chan-Vese Model [77.24463525356566]
  We propose an unsupervised image segmentation approach that integrates the Chan-Vese (CV) model with deep neural networks. Our basic idea is to apply a deep neural network that maps the image into a latent space to alleviate the violation of the piecewise constant assumption in image space.
  arXiv  Detail & Related papers  (2022-04-14T13:23:57Z)
• Cartoon-texture evolution for two-region image segmentation [0.0]
  Two-region image segmentation is a process of dividing an image into two regions of interest, i.e., the foreground and the background. Chan, Esedo=glu, Nikolova, SIAM Journal on Applied Mathematics 66(5), 1632-1648, 2006.
  arXiv  Detail & Related papers  (2022-03-07T16:50:01Z)
• Meta Internal Learning [88.68276505511922]
  Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. We propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. Our results show that the models obtained are as suitable as single-image GANs for many common image applications.
  arXiv  Detail & Related papers  (2021-10-06T16:27:38Z)

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.