Yonsei University

Ki Beom Hong

Hye Ran Byun

Mi Rae Do

Seog Kyu Jeon

A multi-level transferable region-based domain adaptive object detection apparatus includes: an image-level feature part that extracts an image-level feature by providing unlabeled target data to a plurality of convolutional layers; an RPN-level feature part that determines region candidates by providing the image-level feature to a region proposal network (RPN) and performing RPN-level domain adaptation and transferable region filtering; and an instance-level feature part that extracts a region of interest (RoI) pooling feature by conducting dynamic instance sampling on the region candidates.

Growing community of inventors

Seoul, South Korea

Ki Beom Hong