Semantic Predictive Coding with Arbitrated Generative Adversarial Networks

In spatio-temporal predictive coding problems, like next-frame prediction in video, determining the content of plausible future frames is primarily based on the image dynamics of previous frames. We establish an alternative approach based on their underlying semantic information when considering dat...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Machine learning and knowledge extraction Ročník 2; číslo 3; s. 307 - 326
Hlavní autori: Stivaktakis, Radamanthys, Tsagkatakis, Grigorios, Tsakalides, Panagiotis
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: MDPI AG 01.09.2020
Predmet:
deep learning
generative adversarial networks
next-frame prediction
semantic predictive coding
ISSN:2504-4990, 2504-4990
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In spatio-temporal predictive coding problems, like next-frame prediction in video, determining the content of plausible future frames is primarily based on the image dynamics of previous frames. We establish an alternative approach based on their underlying semantic information when considering data that do not necessarily incorporate a temporal aspect, but instead they comply with some form of associative ordering. In this work, we introduce the notion of semantic predictive coding by proposing a novel generative adversarial modeling framework which incorporates the arbiter classifier as a new component. While the generator is primarily tasked with the anticipation of possible next frames, the arbiter’s principal role is the assessment of their credibility. Taking into account that the denotative meaning of each forthcoming element can be encapsulated in a generic label descriptive of its content, a classification loss is introduced along with the adversarial loss. As supported by our experimental findings in a next-digit and a next-letter scenario, the utilization of the arbiter not only results in an enhanced GAN performance, but it also broadens the network’s creative capabilities in terms of the diversity of the generated symbols.
ISSN:2504-4990
2504-4990
DOI:10.3390/make2030017