PixelVAE: A Latent Variable Model for Natural Images

Gulrajani, Ishaan; Kumar, Kundan; Ahmed, Faruk; Taïga, Adrien Ali; Visin, Francesco; Vázquez, David; Courville, Aaron

doi:10.48550/arxiv.1611.05013

Cited by 60 publications

(82 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variational Autoencoders (VAEs) [1,2] are effectively deep generative models that utilize the variational inference and reparameterization trick for dimension reduction [3], learning representations [4], and generating data [5]. And various variants of VAE have been proposed conditioned on advanced variational posterior [6][7][8], powerful decoders [9,10] and flexible priors [10,17,12,13].…”

Section: Bayesian Pseudocoresets Exemplar Vaementioning

confidence: 99%

“…In particular, due to the utilization of the reparameterization trick and variational inference for optimization, Variational Autoencoders (VAEs) [1,2] stand out and have demonstrated significant successes for dimension reduction [3], learning representations [4], and generating data [5]. In addition, various variants of VAE have been proposed conditioned on advanced variational posterior [6][7][8] or powerful decoders [9,10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE

Wen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent studies show that advanced priors play a major role in deep generative models. Exemplar VAE, as a variant of VAE with an exemplar-based prior, has achieved impressive results. However, due to the nature of model design, an exemplar-based model usually requires vast amounts of data to participate in training, which leads to huge computational complexity. To address this issue, we propose Bayesian Pseudocoresets Exemplar VAE (ByPE-VAE), a new variant of VAE with a prior based on Bayesian pseudocoreset. The proposed prior is conditioned on a smallscale pseudocoreset rather than the whole dataset for reducing the computational cost and avoiding overfitting. Simultaneously, we obtain the optimal pseudocoreset via a stochastic optimization algorithm during VAE training aiming to minimize the Kullback-Leibler divergence between the prior based on the pseudocoreset and that based on the whole dataset. Experimental results show that ByPE-VAE can achieve competitive improvements over the state-of-the-art VAEs in the tasks of density estimation, representation learning, and generative data augmentation. Particularly, on a basic VAE architecture, ByPE-VAE is up to 3 times faster than Exemplar VAE while almost holding the performance. Code is available at our supplementary materials.

show abstract

Section: Bayesian Pseudocoresets Exemplar Vaementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE

Wen³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Autoencoder Autoencoders have the ability to learn the effective representation of input data in an unsupervised way. It is mainly used for data compression [13][14][15], representation learning [16,17] and as a generative model [18][19][20]. In the framework of an autoencoder [21,22], an encoder E θ can effectively calculate h = E θ (x) from an input x.…”

Section: Related Workmentioning

confidence: 99%

A Semantic-based Medical Image Fusion Approach

Fan¹,

Huang²,

Wang³

et al. 2019

Preprint

View full text Add to dashboard Cite

It is necessary for clinicians to comprehensively analyze patient information from different sources. Medical image fusion is a promising approach to providing overall information from medical images of different modalities. However, existing medical image fusion approaches ignore the semantics of images, making the fused image difficult to understand. In this paper, we put forward a semanticbased medical image fusion methodology, and as an implementation, we propose a Fusion W-Net (FW-Net) for multimodal medical image fusion. The experimental results are promising: the fused image generated by our approach greatly reduces the semantic information loss, and has comparable visual effects in contrast to the state-of-art approaches. Our approach and tool have great potential to be applied in the clinical setting. The source code of FW-Net is available at https: //github.com/fanfanda/Medical-Image-Fusion.

show abstract

“…(1) VAE has shown promising ability to generate complicated data, including faces [11], natural images [8], text [25] and segmentation [10,27]. Following IntroVAE [11], we adopt introspective adversarial learning in our method to produce high-quality and realistic face images.…”

Section: Variational Autoencodermentioning

confidence: 99%

UVA: A Universal Variational Framework for Continuous Age Analysis

Li¹,

Huang²,

Hu³

et al. 2019

Preprint

View full text Add to dashboard Cite

Conventional methods for facial age analysis tend to utilize accurate age labels in a supervised way. However, existing age datasets lies in a limited range of ages, leading to a long-tailed distribution. To alleviate the problem, this paper proposes a Universal Variational Aging (UVA) framework to formulate facial age priors in a disentangling manner. Benefiting from the variational evidence lower bound, the facial images are encoded and disentangled into an ageirrelevant distribution and an age-related distribution in the latent space. A conditional introspective adversarial learning mechanism is introduced to boost the image quality. In this way, when manipulating the age-related distribution, UVA can achieve age translation with arbitrary ages. Further, by sampling noise from the age-irrelevant distribution, we can generate photorealistic facial images with a specific age. Moreover, given an input face image, the mean value of age-related distribution can be treated as an age estimator. These indicate that UVA can efficiently and accurately estimate the age-related distribution by a disentangling manner, even if the training dataset performs a long-tailed age distribution. UVA is the first attempt to achieve facial age analysis tasks, including age translation, age generation and age estimation, in a universal framework. The qualitative and quantitative experiments demonstrate the superiority of UVA on five popular datasets, including CACD2000, Morph, UTKFace, MegaAge-Asian and FG-NET.

show abstract

PixelVAE: A Latent Variable Model for Natural Images

Cited by 60 publications

References 0 publications

ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE

ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE

A Semantic-based Medical Image Fusion Approach

UVA: A Universal Variational Framework for Continuous Age Analysis

Contact Info

Product

Resources

About