URCA-GAN: UpSample Residual Channel-wise Attention Generative Adversarial Network for image-to-image translation

Nie, Xuan; Ding, Haoxuan; Qi, Manhua; Wang, Yifei; Wong, Edward K.

doi:10.1016/j.neucom.2021.02.054

Cited by 19 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, CycleGAN (J.-Y. Zhu et al, 2017), URCA-GAN (Nie et al, 2021), CSGAN (Babu & Dubey, 2021), and PLDT (Yoo et al, 2016) were proposed to transfer image-to-image while keeping the semantic relation between both source and target domains. Also, RPD-GAN (Gao et al, 2020) proposed a framework for the automatic generation of realistic paintings instead of transferring the styles of artistic paintings.…”

Section: Image-to-image Translationmentioning

confidence: 99%

“…Wang et al, 2018), generating videos and predicting the next scenes (Nakahira & Kawamoto, 2019;Sushko et al, 2021;Tulyakov et al, 2018;J. Zhang, Xu, et al, 2020), translating images between different domains (Babu & Dubey, 2021;Gao et al, 2020;Nie et al, 2021;Yoo et al, 2016;J.-Y. Zhu et al, 2017), editing images (Y.…”

Section: Gan Applicationsmentioning

confidence: 99%

“…Liu, Wan, et al, 2021), translating data between different domains (Babu & Dubey, 2021;Barzilay et al, 2021;Gao et al, 2020;Y. Li, Gan, et al, 2019;Nie et al, 2021;H. Park et al, 2018;Reed et al, 2016;J.-Y.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, GANs can be applied in various domains including enhancing the resolution of images (Karnewar & Wang, 2020; Y. Liu, Fan, et al, 2022; Odena et al, 2017; Shamsolmoali et al, 2019; Sun et al, 2021; L. Wang et al, 2018), completing the destroyed parts of images (Denton et al, 2016; Hassanpour et al, 2022; Jam et al, 2021; Kottler et al, 2022; H. Liu, Wan, et al, 2021), translating data between different domains (Babu & Dubey, 2021; Barzilay et al, 2021; Gao et al, 2020; Y. Liu, Chen, et al, 2021; Y. Li, Gan, et al, 2019; Nie et al, 2021; H. Park et al, 2018; Reed et al, 2016; J.‐Y. Zhu et al, 2017), predicting new behaviors of humans and expected poses (Barsoum et al, 2018; R. Cui et al, 2020; Q. Cui et al, 2021; Jain et al, 2020; L. Ma et al, 2021; Men et al, 2022; L. Tian et al, 2021; Yamane et al, 2020), generating synthetic data of a specific task (Chaudhari et al, 2019; A. Gupta & Zou, 2019; Iqbal & Ali, 2018; Karbhari et al, 2021; Waheed et al, 2020), enhancing speech, and removing noisy signals (Baby & Verhulst, 2019; Kim et al, 2021; G. Liu, Gong, et al, 2020; Mogren, 2016; Pascual et al, 2017; Phan et al, 2020; Qiu et al, 2022; Ram et al, 2020; Y. Wang et al, 2020; J. Wu et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Mohammed

2023

WIREs Computational Stats

View full text Add to dashboard Cite

In machine learning, a generative model is responsible for generating new samples of data in terms of a probabilistic model. Generative adversarial network (GAN) has been widely used to generate realistic samples in different domains and outperforms its peers in the generative models family. However, producing a robust GAN model is not a trivial task because many challenges face the GAN during the training process and impact its performance, affecting the quality and diversity of the generated samples. In this article, we conduct a comprehensive review of GANs to present the fundamentals of GAN, including its components, types, and objective functions. Also, we present an overview of the evaluation matrices used to evaluate GAN models. Moreover, we list the applications of GANs and research work in various domains. Finally, we present the challenges that face GANs and highlight two significant issues, representing mode collapse and training instability, in addition to those research efforts that tackle these challenges.This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Deep Learning Statistical Learning and Exploratory Methods of the Data Sciences > Neural Networks

show abstract

Section: Image-to-image Translationmentioning

confidence: 99%

Section: Gan Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Mohammed

2023

WIREs Computational Stats

View full text Add to dashboard Cite

show abstract

“…There are other examples of channel and spatial vanilla attention: ECA-Net (Efficient Channel Attention) by Wang et al [14] is a new version of Squeeze and Excitation; SCA-CNN (Spatial and Channel-wise attention) proposed by Chen et al [15] combines both spatial and channel vanilla attention for image captioning. URCA-GAN by Nie et al [16] is a GAN (Generative Adversarial Network) featuring a residual channel attention mechanism thought for image-to-image translation.…”

Section: Related Work 11 Attentionmentioning

confidence: 99%

Local Multi-Head Channel Self-Attention for Facial Expression Recognition

Pecoraro¹,

Basile²,

Bono³

et al. 2021

Preprint

View full text Add to dashboard Cite

Since the Transformer architecture was introduced in 2017 there has been many attempts to bring the selfattention paradigm in the field of computer vision. In this paper we propose a novel self-attention module that can be easily integrated in virtually every convolutional neural network and that is specifically designed for computer vision, the LHC: Local (multi) Head Channel (self-attention). LHC is based on two main ideas: first, we think that in computer vision the best way to leverage the self-attention paradigm is the channel-wise application instead of the more explored spatial attention and that convolution will not be replaced by attention modules like recurrent networks were in NLP; second, a local approach has the potential to better overcome the limitations of convolution than global attention. With LHC-Net we managed to achieve a new state of the art in the famous FER2013 dataset with a significantly lower complexity and impact on the "host" architecture in terms of computational cost when compared with the previous SOTA.

show abstract

Accurate and Rapid Localization of Tea Bud Leaf Picking Point Based on YOLOv8

2023

Big Data and Social Computing

View full text Add to dashboard Cite

URCA-GAN: UpSample Residual Channel-wise Attention Generative Adversarial Network for image-to-image translation

Cited by 19 publications

References 27 publications

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Local Multi-Head Channel Self-Attention for Facial Expression Recognition

Accurate and Rapid Localization of Tea Bud Leaf Picking Point Based on YOLOv8

Contact Info

Product

Resources

About