HashBox: Hash Hierarchical Segmentation exploiting Bounding Box Object Detection

We propose a novel approach to address the Simultaneous Detection and Segmentation problem introduced in [8]. Using the hierarchical structures first presented in [1] we use an efficient and accurate procedure that exploits the hierarchy feature information using Locality Sensitive Hashing. We build on recent work that utilizes convolutional neural networks to detect bounding boxes in an image (Faster R-CNN [11]) and then use the top similar hierarchical region that best fits each bounding box after hashing, we call this approach HashBox. We then refine our final segmentation results by automatic hierarchy pruning. HashBox introduces a train-free alternative to Hypercolumns [7]. We conduct extensive experiments on Pascal VOC 2012 segmentation dataset, showing that HashBox gives competitive state-of-the-art object segmentations.