A Style-Based Generator Architecture for Generative Adversarial Networks
Tero Karras,Samuli Laine,Timo Aila +2 more
- pp 4396-4405
Reads0
Chats0
TLDR
This paper proposed an alternative generator architecture for GANs, borrowing from style transfer literature, which 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.Abstract:
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 distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. To quantify interpolation quality and disentanglement, we propose two new, automated methods that are applicable to any generator architecture. Finally, we introduce a new, highly varied and high-quality dataset of human faces.read more
Citations
More filters
Proceedings ArticleDOI
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
Ryan Steed,Aylin Caliskan +1 more
TL;DR: It is found that state-of-the-art unsupervised models trained on ImageNet, a popular benchmark image dataset curated from internet images, automatically learn racial, gender, and intersectional biases.
Proceedings Article
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
TL;DR: In this paper, feature-wise transformation layers for augmenting the image features using affine transforms to simulate various feature distributions under different domains in the training stage are used to solve the problem of few-shot classification under domain shifts.
Journal ArticleDOI
Image synthesis with adversarial networks: A comprehensive survey and case studies
Pourya Shamsolmoali,Pourya Shamsolmoali,Masoumeh Zareapoor,Eric Granger,Huiyu Zhou,Ruili Wang,M. Emre Celebi,Jie Yang +7 more
TL;DR: This survey provides a comprehensive review of adversarial models for image synthesis, and summarizes the synthetic image generation methods, and discusses the categories including image-to-image translation, fusion image generation, label- to-image mapping, and text-to -image translation.
Book ChapterDOI
Neural Design Network: Graphic Layout Generation with Constraints
TL;DR: A method for design layout generation that can satisfy user-specified constraints and is demonstrated to be visually similar to real design layouts is proposed.
Proceedings ArticleDOI
Representative Forgery Mining for Fake Face Detection
Chengrui Wang,Weihong Deng +1 more
TL;DR: Wang et al. as discussed by the authors proposed an attention-based data augmentation framework to guide the detector to refine and enlarge its attention to mine deeper into the regions ignored before for more representative forgery.