Segmenting and refining images with SharpMask

Introduced DeepMask, a segmentation framework that treats segmentation as a series of binary classification problems for image patches and pixels. Developed SharpMask, a refinement module that uses earlier network layer features to improve the fidelity of object masks generated by DeepMask. Proposed MultiPathNet, a specialized convolutional network architecture designed to exploit information at multiple image scales and surrounding context for improved object classification accuracy, building upon the RCNN paradigm.