Salient Object Detection with Pretrained Deeplab and k-Means: Application to UAV-Captured Building Imagery

We present a simple technique that can convert a pretrained segmentation neural network to a salient object detector. We show that the pretrained network can be agnostic to the semantic class of the object of interest, and no further training is required. Experiments were run on UAV-captured aerial imagery of the “smart home” structure located in the premises of the CERTH research center. Further experiments were also run on natural scenes. Our tests validate the usefulness of the proposed technique.