SW-VAE: Weakly Supervised Learn Disentangled Representation via Latent Factor Swapping

Jiageng Zhu; Hanchen Xie; Wael AbdAlmageed

doi:10.1007/978-3-031-25063-7_5

ScienceGate Book Chapters

BOOK-CHAPTER

SW-VAE: Weakly Supervised Learn Disentangled Representation via Latent Factor Swapping

Jiageng Zhu Hanchen Xie Wael AbdAlmageed

Year: 2023 Lecture notes in computer science Pages: 73-87 Publisher: Springer Science+Business Media

DOI: 10.1007/978-3-031-25063-7_5

Get Full-Text PDF Get Analytical Report

Keywords:

Representation (politics) Computer science Feature learning Artificial intelligence Machine learning Process (computing) Generative model Generative grammar Training set Labeled data Factor (programming language) SIGNAL (programming language) Pattern recognition (psychology)

Metrics

Cited By

1.07

FWCI (Field Weighted Citation Impact)

Refs

0.74

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Digital Media Forensic Detection

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Adversarial Robustness in Machine Learning

Physical Sciences → Computer Science → Artificial Intelligence

Advanced Malware Detection Techniques

Physical Sciences → Computer Science → Signal Processing

SW-VAE: Weakly Supervised Learn Disentangled Representation via Latent Factor Swapping

Metrics

Citation History

Topics

Related Documents

q-VAE for Disentangled Representation Learning and Latent Dynamical Systems

Weakly Supervised Disentangled Representation for Goal-Conditioned Reinforcement Learning

SSDMM-VAE: variational multi-modal disentangled representation learning

Private-Shared Disentangled Multimodal VAE for Learning of Latent Representations

Ambient Illumination Disentangled Based Weakly-Supervised Image Restoration Using Adaptive Pixel Retention Factor