Learning a Sequential Search for Landmarks

Saurabh Singh, Derek Hoiem, David Forsyth; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3422-3430

We propose a general method to find landmarks in images of objects using both appearance and spatial context. This method is applied without changes to two problems: parsing human body layouts, and finding landmarks in images of birds. Our method learns a sequential search for localizing landmarks, iteratively detecting new landmarks given the appearance and contextual information from the already detected ones. The choice of landmark to be added is opportunistic and depends on the image; for example, in one image a head-shoulder group might be expanded to a head-shoulder-hip group but in a different image to a head-shoulder-elbow group. The choice of initial landmark is similarly image dependent. Groups are scored using a learned function, which is used to expand them greedily. Our scoring function is learned from data labelled with landmarks but without any labeling of a detection order. Our method represents a novel spatial model for the kinematics of groups of landmarks, and displays strong performance on two different model problems.