Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

2018-02-27 · ICML 2018 7 · Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data. CycleGAN was recently proposed for this problem, but critically assumes the underlying inter-domain mapping is approximately deterministic and one-to-one. This assumption renders the model ineffective for tasks requiring flexible, many-to-many mappings. We propose a new model, called Augmented CycleGAN, which learns many-to-many mappings between domains. We examine Augmented CycleGAN qualitatively and quantitatively on several image datasets.

📄 PDF Abstract BibTeX arXiv:1802.10151

Code (3)

ErfanMN/Augmented_CycleGAN_Pytorch pytorch

NathanDeMaria/AugmentedCycleGAN pytorch

aalmah/augmented_cyclegan pytorch

Tasks

Image Segmentation Semantic Segmentation Structured Prediction

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음

Residual Connection 설명 없음

PatchGAN 설명 없음

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Tanh Activation 설명 없음

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Instance Normalization Instance Normalization (also known as contrast normalization) is a normalization layer where: $$ y_{tijk} = \frac{x_{tijk} - \mu_{ti}}{\sqrt{\sigma_{ti}^2 +…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation

2022-03-04 · Dmitrii Torbunov, Yi Huang, Haiwang Yu, Jin Huang 외

Unpaired image-to-image translation has broad applications in art, design, and scientific simulations. One early breakthrough was CycleGAN that emphasizes one-to-one mappings between two unpaired image domains via genera…

Diversity Image-to-Image Translation Translation

Unified Microphone Conversion: Many-to-Many Device Mapping via Feature-wise Linear Modulation

2024-10-23 · Myeonghoon Ryu, Hongseok Oh, Suji Lee, Han Park

We present Unified Microphone Conversion, a unified generative framework designed to bolster sound event classification (SEC) systems against device variability. While our prior CycleGAN-based methods effectively simulat…

Theoretical Insights into CycleGAN: Analyzing Approximation and Estimation Errors in Unpaired Data Generation

2024-07-16 · Luwei Sun, Dongrui Shen, Han Feng

In this paper, we focus on analyzing the excess risk of the unpaired data generation model, called CycleGAN. Unlike classical GANs, CycleGAN not only transforms data between two unpaired distributions but also ensures th…

Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks

2017-11-30 · Takuhiro Kaneko, Hirokazu Kameoka

We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data…

Voice Conversion

CycleGAN with Better Cycles

2024-08-27 · Tongzhou Wang, Yihan Lin

CycleGAN provides a framework to train image-to-image translation with unpaired datasets using cycle consistency loss [4]. While results are great in many applications, the pixel level cycle consistency can potentially b…

Image-to-Image Translation Translation