One Shot Learning for Generic Instance Segmentation in RGBD Videos

Xiao Lin, Josep Casas, Montse Pardàs
2019 Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
Hand-crafted features employed in classical generic instance segmentation methods have limited discriminative power to distinguish different objects in the scene, while Convolutional Neural Networks (CNNs) based semantic segmentation is restricted to predefined semantics and not aware of object instances. In this paper, we combine the advantages of the two methodologies and apply the combined approach to solve a generic instance segmentation problem in RGBD video sequences. In practice, a
more » ... cal generic instance segmentation method is employed to initially detect object instances and build temporal correspondences, whereas instance models are trained based on the few detected instance samples via CNNs to generate robust features for instance segmentation. We exploit the idea of one shot learning to deal with the small training sample size problem when training CNNs. Experiment results illustrate the promising performance of the proposed approach.
doi:10.5220/0007259902330239 dblp:conf/visapp/0003CP19 fatcat:gah4s4mhkrbqtc52dhigzje6jy