L-VAE: variational auto-encoder with learnable beta for disentangled representation

Hazal Mogultay Ozcan; Sinan Kalkan; Fatoş T. Yarman-Vural

doi:10.1007/s00138-025-01728-2

ScienceGate Book Chapters

JOURNAL ARTICLE

L-VAE: variational auto-encoder with learnable beta for disentangled representation

Hazal Mogultay Ozcan Sinan Kalkan Fatoş T. Yarman-Vural

Year: 2025 Journal: Machine Vision and Applications Vol: 36 (5) Publisher: Springer Science+Business Media

DOI: 10.1007/s00138-025-01728-2

Get Full-Text PDF Get Analytical Report

Keywords:

BETA (programming language) Representation (politics) Autoencoder Encoder Mathematics Computer science Artificial intelligence Statistics Artificial neural network Programming language

Metrics

Cited By

0.00

FWCI (Field Weighted Citation Impact)

Refs

0.25

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Topics

Generative Adversarial Networks and Image Synthesis

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Digital Media Forensic Detection

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Music and Audio Processing

Physical Sciences → Computer Science → Signal Processing

L-VAE: variational auto-encoder with learnable beta for disentangled representation

Metrics

Topics

Related Documents

Causal Flow-Based Variational Auto-Encoder for Disentangled Causal Representation Learning

Electric Machine Inverse Design with Variational Auto-Encoder (VAE)

HVQ-VAE: Variational auto-encoder with hyperbolic vector quantization

SSDMM-VAE: variational multi-modal disentangled representation learning

Disentangled Variational Auto-Encoder for semi-supervised learning