Traditional supervised learning requires significant amounts of labeled training data to achieve satisfactory results. As autonomous perception systems collect continuous data, the labeling process becomes expensive and ...

The following pages explore the use of generative models for realistic image anonymization. In summary, this thesis aims to address two primary objectives. First, develop generative models for synthesizing human figures ...

We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively ...

Tradisjonelle bildeanonymiseringsteknikker er ofte ødeleggende for datadistribusjonen, noe som gjør bildene uegnet for maskinlæringsmodeller. Imidlertid krever disse modellene en enorm mengde data, som personvernlover som ...

Det finnes mange datasystemer som krever store mengder bildedata, men tilgjengeligheten og kvaliteten på denne bildedataen begrenses ofte av personvenrnsreguleringer som \acrshort{gdpr}. Et problem er at banale ...