DuCaGAN: Unified Dual Capsule Generative Adversarial Network for Unsupervised Image-to-Image Translation

Shao, Guifang; Huang, Meng; Gao, Fengqiang; Liu, Tundong; Li, Liduan

doi:10.1109/access.2020.3007266

Cited by 15 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used the teacher forcing scheme with a pretraining algorithm to improve the training efficiency and stability during the generative model implementation process. Shao et al [38] incorporated GAN into the capsule network for the better utilization of view angle invariance and rotation equivariance in image-to-image translation issues.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization

Zhou,

Zheng,

Shu

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms. In particular, an ITL-and CRL-enhanced Dual-GAN (ITCRL-DGAN) model is presented, which includes an autoencoder with CRL (AE-CRL) structure to aid the dual-adversarial training with causality-inspired feature representations and a Dual-GAN structure to improve the data augmentation in both feature and data levels. Following a newly designed feature separation strategy, a causal graph is built and improved based on the Manuscript

show abstract

Section: Generative Adversarial Networkmentioning

confidence: 99%

Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization

Zhou,

Zheng,

Shu

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Also, L. Cai, Chen, et al (2020) proposed an optimized objective function to minimize the

α

‐divergence to keep balance during the training process. Likewise, Shao et al (2020) focused on optimizing the objective function of their proposed GAN model to stabilize the training process.…”

Section: Gan Challengesmentioning

confidence: 99%

“…Tran et al, 2018; G. Wang et al, 2022; B. Zhang, Gu, et al, 2022). Approaches focused on optimizing the objective function (Abusitta et al, 2021; Arjovsky et al, 2017; L. Cai, Chen, et al, 2020; Gnanha et al, 2022; Huang et al, 2021; Karnewar & Wang, 2020; Murray & Rawat, 2022; Pei et al, 2021; Shao et al, 2020; Tao & Wang, 2020; N.‐T. Tran, Bui, & Cheung, 2019; Yao et al, 2019; Zadorozhnyy et al, 2021; Z. Zhou, Zhong, et al, 2020).…”

Section: Gan Challengesmentioning

confidence: 99%

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

“…Structural similarity index metric (SSIM) : This index has been extensively utilized to assess image quality [ 7 ] and has been used as loss function for numerous image processing applications [ 35 , 36 ] as well as for GAN-based solutions [ 32 , 37 , 38 ]. It was created under the presumption that the human visual system is extremely well suited for sifting through structural data in a visual input.…”

Section: Generating Synthesized Defective Images Via Cycleganmentioning

confidence: 99%

Generating Defective Epoxy Drop Images for Die Attachment in Integrated Circuit Manufacturing via Enhanced Loss Function CycleGAN

Alam

Kehtarnavaz

2023

Sensors

View full text Add to dashboard Cite

In integrated circuit manufacturing, defects in epoxy drops for die attachments are required to be identified during production. Modern identification techniques based on vision-based deep neural networks require the availability of a very large number of defect and non-defect epoxy drop images. In practice, however, very few defective epoxy drop images are available. This paper presents a generative adversarial network solution to generate synthesized defective epoxy drop images as a data augmentation approach so that vision-based deep neural networks can be trained or tested using such images. More specifically, the so-called CycleGAN variation of the generative adversarial network is used by enhancing its cycle consistency loss function with two other loss functions consisting of learned perceptual image patch similarity (LPIPS) and a structural similarity index metric (SSIM). The results obtained indicate that when using the enhanced loss function, the quality of synthesized defective epoxy drop images are improved by 59%, 12%, and 131% for the metrics of the peak signal-to-noise ratio (PSNR), universal image quality index (UQI), and visual information fidelity (VIF), respectively, compared to the CycleGAN standard loss function. A typical image classifier is used to show the improvement in the identification outcome when using the synthesized images generated by the developed data augmentation approach.

show abstract

DuCaGAN: Unified Dual Capsule Generative Adversarial Network for Unsupervised Image-to-Image Translation

Abstract: Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

Cited by 15 publications

References 23 publications

Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization

Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization

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

Generating Defective Epoxy Drop Images for Die Attachment in Integrated Circuit Manufacturing via Enhanced Loss Function CycleGAN

Contact Info

Product

Resources

About