SEMANTIC OBJECT REGION SEGMENTATION METHOD AND SYSTEM BASED ON WEAK MAP LEARNING OBJECT DETECTOR

摘要

A semantic object region segmentation technique based on a weak supervised learning object detector is disclosed. A computer-implemented system according to an embodiment includes at least one processor that is implemented to execute computer-readable instructions, and the at least one processor inputs an image into a plurality of branches configured in an object area division network. Inputs; A detection unit for detecting an object region by an object detector trained to detect an object from the image; And a dividing unit for segmenting an instance as learning by using the information of the detected object region and a bounding box associated with the detected object region.