Coupled generative adversarial stacked Auto-encoder: CoGASA

Kiasari, Mohammad Ahangar; Moirangthem, Dennis Singh; Lee, Minho

doi:10.1016/j.neunet.2018.01.002

Cited by 22 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second one keeps its own parameters frozen. Several variants of the GANs have recently been developed from the original fully-connected architecture proposed by Goodfellow [282] such as convolutional GANs, conditional GANs, adversarial autoencoders (AAE) and class experts GAN (see [281,[283][284][285][286]). GANs are recently applied in all biomedical fields such as in the Omics for a protein modeling by Li et al [156], who considered loop modeling as an image inpainting problem with the generative network having to capture the context of the loop region with a prediction of the missing area.…”

Section: Emergent Architectures: the Generative Adversarial Networkmentioning

confidence: 99%

Deep Learning in the Biomedical Applications: Recent and Future Status

2019

View full text Add to dashboard Cite

Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

show abstract

Section: Emergent Architectures: the Generative Adversarial Networkmentioning

confidence: 99%

Deep Learning in the Biomedical Applications: Recent and Future Status

2019

View full text Add to dashboard Cite

show abstract

“…Generative Adversarial Networks (GAN for short) proposed by Goodfellow et al [19] is one of the most prominent deep generative model. This powerful technique and its varieties such as CoGAN [26], Triple-GAN [33], AdaGAN [65], AL-CGAN [25], CGAN [51], BiGAN [13], CycleGAN [108], DCGAN [57], etc. are often utilized to solve wide variety of computer vision and pattern recognition problems, such as image-to-image translation and person Re-Id.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

PAC-GAN: An effective pose augmentation scheme for unsupervised cross-view person re-identification

et al. 2020

View full text Add to dashboard Cite

Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based methods to enhance the recognition rate in a supervised or unsupervised manner. However, two limitations that cannot be ignored: firstly, compared with other image retrieval benchmarks, the size of existing person Re-Id datasets are far from meeting the requirement, which cannot provide sufficient pedestrian samples for the training of deep model; secondly, the samples in existing datasets do not have sufficient human motions or postures coverage to provide more priori knowledges for learning. In this paper, we introduce a novel unsupervised pose augmentation cross-view person Re-Id scheme called PAC-GAN to overcome these limitations. We firstly present the formal definition of cross-view pose augmentation and then propose the framework of PAC-GAN that is a novel conditional generative adversarial network (CGAN) based approach to improve the performance of unsupervised corss-view person Re-Id. Specifically, The pose generation model in PAC-GAN called CPG-Net is to generate enough quantity of pose-rich samples from original image and skeleton samples. The pose augmentation dataset is produced by combining the synthesized poserich samples with the original samples, which is fed into the corss-view person Re-Id model named Cross-GAN. Besides, we use weight-sharing strategy in the CPG-Net to improve the quality of new generated samples. To the best of our knowledge, we are the first try to enhance the unsupervised cross-view person Re-Id by pose augmentation, and the results of extensive experiments show that the proposed scheme can combat the state-of-the-arts.

show abstract

“…Several attempts have been made to couple multiple GANs for domain adaptation. Specifically [18] and [28] proposed coupled GAN architectures for generating images in different domains with a joint random vector input. However we are considering multi-modal input streams of the same action representation, and are modelling videos as opposed to a single image.…”

Section: Related Workmentioning

confidence: 99%

Coupled Generative Adversarial Network for Continuous Fine-Grained Action Segmentation

Gammulle

Fernando

Denman

et al. 2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We propose a novel conditional GAN (cGAN) model for continuous fine-grained human action segmentation, that utilises multi-modal data and learned scene context information. The proposed approach utilises two GANs: termed Action GAN and Auxiliary GAN, where the Action GAN is trained to operate over the current RGB frame while the Auxiliary GAN utilises supplementary information such as depth or optical flow. The goal of both GANs is to generate similar 'action codes', a vector representation of the current action. To facilitate this process a context extractor that incorporates data and recent outputs from both modes is used to extract context information to aid recognition. The result is a recurrent GAN architecture which learns a task specific loss function from multiple feature modalities. Extensive evaluations on variants of the proposed model to show the importance of utilising different information streams such as context and auxiliary information in the proposed network; and show that our model is capable of outperforming state-of-the-art methods for three widely used datasets: 50 Salads, MERL Shopping and Georgia Tech Egocentric Activities, comprising both static and dynamic camera settings. 1

show abstract

Coupled generative adversarial stacked Auto-encoder: CoGASA

Cited by 22 publications

References 6 publications

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep Learning in the Biomedical Applications: Recent and Future Status

PAC-GAN: An effective pose augmentation scheme for unsupervised cross-view person re-identification

Coupled Generative Adversarial Network for Continuous Fine-Grained Action Segmentation

Contact Info

Product

Resources

About