VGG16 pre-trained on VGGFACE, label 238

Index: HOME / VGGFACE / VGG16 / label 238

Red numbers denote the target confidence. For the white-box inversion, we run with a batch size of 8. For the black-box inversion, AMI only returns 1 image so we only generate 1 image.

Target Person

8 images of the target person with the largest file size from VGGFACE

GMI (white-box)

PGGAN (white-box)

MIRROR (ours white-box)

MIRROR (ours white-box with random dropout)

AMI (black-box)

MIRROR (ours black-box)