In this paper we address the problem of establishing correspondences between different instances of the same object. The problem is posed as finding the geometric transformation that aligns a given image pair. We use a convolutional neural network (CNN) to directly regress the parameters of the transformation model. The alignment problem is defined in the setting where an unordered set of semantic key-points per image are available, but, without the correspondence information. To this end we propose a novel loss function based on cyclic consistency that solves this 2D point set registration problem by inferring the optimal geometric transformation model parameters. We train and test our approach on a standard benchmark dataset Proposal-Flow (PF-PASCAL)\cite{proposal_flow}. The proposed approach achieves state-of-the-art results demonstrating the effectiveness of the method. In addition, we show our approach further benefits from additional training samples in PF-PASCAL generated by using category level information.
@article{arxiv.1901.08341,
title = {Semantic Matching by Weakly Supervised 2D Point Set Registration},
author = {Zakaria Laskar and Hamed R. Tavakoli and Juho Kannala},
journal= {arXiv preprint arXiv:1901.08341},
year = {2019}
}