A Style-Based Generator Architecture for Generative Adversarial Networks

@article{Karras2021ASG,
  title={A Style-Based Generator Architecture for Generative Adversarial Networks},
  author={Tero Karras and Samuli Laine and Timo Aila},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2021},
  volume={43},
  pages={4217-4228}
}
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional… 
SphericGAN: Semi-supervised Hyper-spherical Generative Adversarial Networks for Fine-grained Image Synthesis
TLDR
This work proposes a semi-supervised hyper-spherical GAN for class-conditional image generation, and its model is referred to as SphericGAN, which achieves state-of-the-art performance in synthesizing high-fidelity images with precise class semantics.
Fractional Wavelet-Based Generative Scattering Networks
TLDR
A new dimensionality reduction method named feature-map fusion (FMF) is developed instead of performing PCA to better retain the information of FrScatNets, and the effect of image fusion on the quality of the generated image is discussed.
Learning Disentangled Representations with Latent Variation Predictability
TLDR
The proposed variation predictability is a general constraint that is applicable to the VAE and GAN frameworks for boosting disentangled latent representations and correlates well with existing ground-truth-required metrics and the proposed algorithm is effective for disentanglement learning.
Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation
TLDR
A novel adversarial derived data augmentation methodology that aims to enable dataset balance at a per-subject level via the use of image-to-image transformation for the transfer of sensitive racial characteristic facial features.
Generative Adversarial Network Technologies and Applications in Computer Vision
TLDR
The theoretical basis of GANs is reviewed and some recently developed GAN models are surveyed, in comparison with traditional G AN models, for computer vision applications.
Generative Adversarial Networks to Improve Fetal Brain Fine-Grained Plane Classification
TLDR
The experimental results show that using data generated by both GANs and classical augmentation strategies allows for increasing the accuracy and area under the curve score.
HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models
TLDR
This work establishes a gold standard human benchmark for generative realism by constructing Human eYe Perceptual Evaluation (HYPE), a human benchmark that is grounded in psychophysics research in perception, reliable across different sets of randomly sampled outputs from a model, able to produce separable model performances, and efficient in cost and time.
AutoML: A Survey of the State-of-the-Art
Painting from Part
TLDR
A novel part-painting method according to the observations of relationship between part and whole, which consists of three stages: part-noise restarting, part-feature repainting, and part-patch refining, to paint the whole image by leveraging both feature-level and patch-level part as well as powerful representation ability of generative adversarial network.
Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
TLDR
A novel High-resolution and Diversified VI deo- LA nguage pre-training model (HD-VILA) for many visual tasks that achieves new state-of-the-art results in 10 VL understanding tasks and 2 more novel text-to-visual generation tasks.
...
...