The LCFI website uses cookies only for anonymised website statistics and for ensuring our security, never for tracking or identifying you individually. To find out more, and to find out how we protect your personal information, please read our privacy policy.

Exploring Properties of the Deep Image Prior

Conference Paper by Andreas Kattamis, Tameem Adel Hesham, Adrian Weller

Exploring Properties of the Deep Image Prior. NeurIPS Workshop on Solving inverse problems with deep networks, Vancouver, 2019. 

The Deep Image Prior (DIP, Ulyanov et al., 2017) is a fascinating recent approach for recovering images which appear natural, yet is not fully understood. This work investigates the properties of the early outputs of the DIP. First, we show that these early iterations demonstrate invariance to adversarial perturbations by classifying progressive DIP outputs and using a novel saliency map approach. Next we explore using DIP as a defence against adversaries, showing good potential. Finally, we examine the adversarial invariancy of the early DIP outputs, and hypothesize that these outputs may remove non-robust image features. By comparing classification confidence values we show some evidence confirming this hypothesis.

Download Conference Paper