One-Shot Domain Adaptation for Face Generation

@article{Yang2020OneShotDA,
  title={One-Shot Domain Adaptation for Face Generation},
  author={Chao Yang and Ser-Nam Lim},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={5920-5929}
}
  • Chao Yang, Ser-Nam Lim
  • Published 28 March 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we propose a framework capable of generating face images that fall into the same distribution as that of a given one-shot example. We leverage a pre-trained StyleGAN model that already learned the generic face distribution. Given the one-shot target, we develop an iterative optimization scheme that rapidly adapts the weights of the model to shift the output's high-level distribution to the target's. To generate images of the same distribution, we introduce a style-mixing… 
One-shot domain adaptation for semantic face editing of real world images using StyleALAE
TLDR
This work uses a recent advancement in one-shot domain adaptation to address the application of styleALAE for semantic face editing of images with known identities and ensures that the identity of the reconstructed image is the same as the given input image.
AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation
TLDR
This paper proposes AniGAN, a novel GAN-based translator that synthesizes highquality anime-faces, and proposes a double-branch discriminator to learn both domain-specific distributions and domain-shared distributions, helping generate visually pleasing anime- faces and effectively mitigate artifacts.
Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
  • Peike Li, Xin Yu, Yi Yang
  • Computer Science
    2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2021
TLDR
A Domain-Aware Pyramid-based Face Super-Resolution network, named DAP-FSR, which makes the first attempt to super-resolve LR faces from a target domain by exploiting only a pair of high-resolution (HR) and LR exemplar in the target domain.
TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
TLDR
A targetoriented hypothesis adaptation network (TOHAN) is proposed to solve the FHA problem, where highly-compatible unlabeled data is generated to help train a target-domain classifier and the private information in SD will be protected well.
Few-shot Forgery Detection via Guided Adversarial Interpolation
TLDR
This work addresses the few-shot forgery detection problem by designing a comprehensive benchmark based on coverage analysis among various forgery approaches, and proposing Guided Adversarial Interpolation (GAI), and enhancing the discriminative ability against novel forgery approach via adversarially interpolating the artifacts of the minority samples to the majority samples under the guidance of a teacher network.
Generalizing Face Forgery Detection with High-frequency Features
TLDR
This paper finds that current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize, and proposes to utilize the high-frequency noises for face forgery detection with superior generalization performance.
Speech2Video: Cross-Modal Distillation for Speech to Video Generation
TLDR
A light-weight, cross-modal distillation method to extract disentangled emotional and identity information from unlabelled video inputs is proposed and outperforms the existing algorithms in terms of emotion expression in the generated videos.
Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
TLDR
A novel single-center loss (SCL) is designed that only compresses intra-class variations of natural faces while boosting inter-class differences in the embedding space and can learn more discriminative features with less optimization difficulty.
I-GANs for Infrared Image Generation
TLDR
The experimental results reveal that high-quality and reliable infrared data are generated by the proposed I-GANs, and the instability and mode collapse of the generated adversarial network training can be alleviated.
Improving Generalization of Deepfake Detection with Domain Adaptive Batch Normalization
TLDR
The proposed Domain Adaptive Batch Normalization (DABN) strategy to mitigate the domain distribution gap on different datasets achieves an average accuracy improvement by nearly 20% of existing strategies on Celeb-DF dataset under black-box settings, indicating strong enhancement of generalization ability of the deepfake detection models.
...
...

References

SHOWING 1-10 OF 53 REFERENCES
AGA: Attribute-Guided Augmentation
TLDR
This work proposes attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data such that an attribute of a synthesized sample is at a desired value or strength.
Few-Shot Adversarial Domain Adaptation
TLDR
This work provides a framework for addressing the problem of supervised domain adaptation with deep models by carefully designing a training scheme whereby the typical binary adversarial discriminator is augmented to distinguish between four different classes.
A Style-Based Generator Architecture for Generative Adversarial Networks
TLDR
An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.
Few-Shot Unsupervised Image-to-Image Translation
TLDR
This model achieves this few-shot generation capability by coupling an adversarial training scheme with a novel network design, and verifies the effectiveness of the proposed framework through extensive experimental validation and comparisons to several baseline methods on benchmark datasets.
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
TLDR
This work presents a system that performs lengthy meta-learning on a large dataset of videos, and is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators.
Unified Deep Supervised Domain Adaptation and Generalization
TLDR
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models by reverting to point-wise surrogates of distribution distances and similarities by exploiting the Siamese architecture.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
TLDR
It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.
Deep appearance models for face rendering
TLDR
A data-driven rendering pipeline that learns a joint representation of facial geometry and appearance from a multiview capture setup and a novel unsupervised technique for mapping images to facial states results in a system that is naturally suited to real-time interactive settings such as Virtual Reality (VR).
Matching Networks for One Shot Learning
TLDR
This work employs ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories to learn a network that maps a small labelled support set and an unlabelled example to its label, obviating the need for fine-tuning to adapt to new class types.
Generative Visual Manipulation on the Natural Image Manifold
TLDR
This paper proposes to learn the natural image manifold directly from data using a generative adversarial neural network, and defines a class of image editing operations, and constrain their output to lie on that learned manifold at all times.
...
...