Deep Face Decoder: Towards understanding the embedding space of convolutional networks through visual reconstruction of deep face templates

Janez Krizaj, Richard Plesh, Mahesh Banavar, Stephanie Schuckers, Vitomir Struc

Abstract: Highlights•We present the Deep Face Decoder (DFD), a novel SOTA template inversion technique.•We use DFD to analyze the embedding space of ConvNet face recognition (FR) models.•Using DFD we explore the impact of image perturbations, occlusions, and attacks.•Through DFD we investigate various template construction strategies.