Zero-shot Generative Model Adaptation via Image-specific Prompt Learning

• URL: http://arxiv.org/abs/2304.03119v1
• Date: Thu, 6 Apr 2023 14:48:13 GMT
• Title: Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
• Authors: Jiayi Guo, Chaofei Wang, You Wu, Eric Zhang, Kai Wang, Xingqian Xu, Shiji Song, Humphrey Shi, Gao Huang
• Abstract summary: CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain. We propose an Image-specific Prompt Learning (IPL) method, which learns specific prompt vectors for each source-domain image. IPL effectively improves the quality and diversity of synthesized images and alleviates the mode collapse.
• Score: 41.344908073632986
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain. It does not require any target-domain samples but only the textual domain labels. The training is highly efficient, e.g., a few minutes. However, existing methods still have some limitations in the quality of generated images and may suffer from the mode collapse issue. A key reason is that a fixed adaptation direction is applied for all cross-domain image pairs, which leads to identical supervision signals. To address this issue, we propose an Image-specific Prompt Learning (IPL) method, which learns specific prompt vectors for each source-domain image. This produces a more precise adaptation direction for every cross-domain image pair, endowing the target-domain generator with greatly enhanced flexibility. Qualitative and quantitative evaluations on various domains demonstrate that IPL effectively improves the quality and diversity of synthesized images and alleviates the mode collapse. Moreover, IPL is independent of the structure of the generative model, such as generative adversarial networks or diffusion models. Code is available at https://github.com/Picsart-AI-Research/IPL-Zero-Shot-Generative-Model-Adaptation.

Related papers

• Diversified in-domain synthesis with efficient fine-tuning for few-shot classification [64.86872227580866]
  Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. We propose DISEF, a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. We validate our method in ten different benchmarks, consistently outperforming baselines and establishing a new state-of-the-art for few-shot classification.
  arXiv  Detail & Related papers  (2023-12-05T17:18:09Z)
• DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains [26.95350186287616]
  Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. We propose DynaGAN, a novel few-shot domain-adaptation method for multiple target domains.
  arXiv  Detail & Related papers  (2022-11-26T12:46:40Z)
• 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)
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation [97.74059510314554]
  Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering from large domain gaps. We propose a novel Dual Soft-Paste (DSP) method in this paper.
  arXiv  Detail & Related papers  (2021-07-20T16:22:40Z)
• Few-Shot Domain Adaptation with Polymorphic Transformers [50.128636842853155]
  Deep neural networks (DNNs) trained on one set of medical images often experience severe performance drop on unseen test images. Few-shot domain adaptation, i.e., adapting a trained model with a handful of annotations, is highly practical and useful in this case. We propose a Polymorphic Transformer (Polyformer) which can be incorporated into any DNN backbone for few-shot domain adaptation.
  arXiv  Detail & Related papers  (2021-07-10T10:08:57Z)
• PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training [4.336877104987131]
  Unsupervised domain adaptation is a promising technique for semantic segmentation. We present a novel framework for unsupervised domain adaptation based on the notion of target-domain consistency training. Our approach is simpler, easier to implement, and more memory-efficient during training.
  arXiv  Detail & Related papers  (2021-05-17T19:36:28Z)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)

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.