A computer-implemented method for representation disentanglement is provided. The method includes encoding an input vector into an embedding. The method further includes learning, by a hardware processor, disentangled representations of the input vector including a style embedding and a content embedding by performing sample-based mutual information minimization on the embedding under a Wasserstein distance regularization and a Kullback-Leibler (KL) divergence. The method also includes decoding the style and content embeddings to obtain a reconstructed vector.
INFORMATION THEORY GUIDED SEQUENTIAL REPRESENTATION DISENTANGLEMENT AND DATA GENERATION
2022-06-02
Patent
Electronic Resource
English
IPC: | G06K Erkennen von Daten , RECOGNITION OF DATA / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G10L Analyse oder Synthese von Sprache , SPEECH ANALYSIS OR SYNTHESIS |
UAV Collision Avoidance in Unknown Scenarios with Causal Representation Disentanglement
DOAJ | 2024
|COMMUTATIVE LIE GROUP VAE FOR DISENTANGLEMENT LEARNING
TIBKAT | 2022
|Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement
ArXiv | 2019
|