Semantic Matching by Weakly Supervised 2D Point Set Registration
This addresses semantic matching for computer vision applications, but appears incremental as it builds on existing weakly supervised point set registration methods.
The paper tackles the problem of establishing correspondences between different instances of the same object by finding geometric transformations that align image pairs, achieving state-of-the-art results on the PF-PASCAL benchmark dataset.
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.