We propose a novel approach for instance segmen- tation given an image of homogeneous object clus- ter (HOC). Our learning approach is one-shot be- cause a single video of an object instance is cap- tured and it requires no human annotation. Our in- tuition is that images of homogeneous objects can be effectively synthesized based on structure and illumination priors derived from real images. A novel solver is proposed that iteratively maximizes our structured likelihood to generate realistic im- ages of HOC. Illumination transformation scheme is applied to make the real and synthetic images share the same illumination condition. Extensive experiments and comparisons are performed to ver- ify our method. We build a dataset consisting of pixel-level annotated images of HOC. The dataset and code will be published with the paper.
@article{arxiv.1802.00383,
title = {Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters},
author = {Zheng Wu and Ruiheng Chang and Jiaxu Ma and Cewu Lu and Chi-Keung Tang},
journal= {arXiv preprint arXiv:1802.00383},
year = {2018}
}