METHOD FOR TRAINING A SINGLE NON-SYMMETRIC DECODER FOR LEARNING-BASED CODECS

A method for creating a non-symmetric codec architecture where a single decoder is able to decode the latent representations produced by different neural encoders. Being a single general decoder, the codec generated does not require multiple symmetric decoders, which saves a large amount of disk spa...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	GARCIA FREITAS, PEDRO, CASTRO DA SILVA, RENAM, TESTONI, VANESSA
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRICITY HANDLING RECORD CARRIERS PHYSICS PICTORIAL COMMUNICATION, e.g. TELEVISION PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	A method for creating a non-symmetric codec architecture where a single decoder is able to decode the latent representations produced by different neural encoders. Being a single general decoder, the codec generated does not require multiple symmetric decoders, which saves a large amount of disk space. Therefore, beyond reducing the complexity in execution runtime, the embodiments presented herein significantly reduces the space complexity of learning-based codecs and saves huge amounts of disk space, enabling real applications specially in mobile devices.