Cloud-VAE: Variational autoencoder with concepts embedded

Liu, Yue; Liu, Zitu; Li, Shuang; Yu, Zhenyao; Guo, Yike; Li, Qun; Wang, Guoyin

doi:10.1016/j.patcog.2023.109530

Cited by 11 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The variational autoencoder is a generative network structure based on the variational bayes inference. In contrast to the traditional autoencoder [6] that describes the latent space numerically, it describes observations of the latent space probabilistically, parameterizes the distribution using the mean and variance of latent variables, learns these parameters by maximizing the likelihood, and generates reconstructed data by decoding from that distribution [7]. It has shown great application in data generation.…”

Section: The Binary Variational Autoencodermentioning

confidence: 99%

Binary variational autoencoder for perceptual vibration hashing

li,

liu

et al. 2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

Machine learning methods can automatically extract inherent structural features in data, thus widely used for vibration feature extraction. However, it is very challenging to make a balance between generalizability and diagnostic accuracy on the extracted features. The variational autoencoder describes the observations in the latent space in a probabilistic way, so that the extracted latent space features have a good generalization ability. This paper develops the Binary Variational Autoencoder (BVAE), dedicated to describing the machine condition information carried by the vibration signals in a probabilistic way. The BVAE maps vibration signals into a latent space to extract machine condition information and binarizes them, resulting in a compact machine condition hash (MCH). The effectiveness of the developed method was verified using the Case Western Reserve University bearing data set. The results show that the machine conditional hash extracted by the BVAE can balance low dimensionality and high discriminability, achieving a diagnostic accuracy over 99%.

show abstract

Section: The Binary Variational Autoencodermentioning

confidence: 99%

Binary variational autoencoder for perceptual vibration hashing

li,

liu

et al. 2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

show abstract

“…In this part, we evaluate the FID of different GAN algorithms to demonstrate the effectiveness of the proposed RCFCA-GAN algorithm. We train ACGAN [37], ACGAN with WGAN-GP loss function [30] (we name this algorithm as "WACGAN-GP"), WACGAN-GP using the single top-k method (we name this algorithm as "Single top-k") and the proposed algorithm implementing only Stage 1 (we name this algorithm as "RCFCA-GAN (Stage 1)"), respectively. The reason why we only implement Stage 1 in this experiment is that FID is used to evaluate the generation results of the GAN model.…”

Section: Fid Of Generated Imagesmentioning

confidence: 99%

“…AE encodes the data into a low-dimensional representation by an encoder and decodes the representation back to the original data. But, as AE uses a small latent dimension, it cannot fit complex distributions and some of its generation results are unsatisfying [30].…”

Section: Introductionmentioning

confidence: 99%

A Two-Stage SAR Image Generation Algorithm Based on GAN with Reinforced Constraint Filtering and Compensation Techniques

Liu,

Wang,

Chen

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Generative adversarial network (GAN) can generate diverse and high-resolution images for data augmentation. However, when GAN is applied to the synthetic aperture radar (SAR) dataset, the generated categories are not of the same quality. The unrealistic category will affect the performance of the subsequent automatic target recognition (ATR). To overcome the problem, we propose a reinforced constraint filtering with compensation afterwards GAN (RCFCA-GAN) algorithm to generate SAR images. The proposed algorithm includes two stages. We focus on improving the quality of easily generated categories in Stage 1. Then, we record the categories that are hard to generate and compensate by using traditional augmentation methods in Stage 2. Thus, the overall quality of the generated images is improved. We conduct experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset. Recognition accuracy and Fréchet inception distance (FID) acquired by the proposed algorithm indicate its effectiveness.

show abstract