Object proposal with kernelized partial ranking

Jing Wang, Jie Shen, Ping Li

Abstract: Highlights • In this paper, we propose a new partial ranking algorithm with support of non- linear kernel. • We perform consistent weighted sampling on the features followed by learning our partial ranking model. Here learning a ranking model with non-linear kernel amounts to learning a linear hyperplane. • Our algorithm greatly promotes baseline proposal generation methods in recall and average recall. • Our method can be integrated with any proposal generation methods. Abstract Object proposals are an ensemble of bounding boxes with high potential to contain objects. In order to determine a small set of proposals with a high recall, a common scheme is extracting multiple features followed by a ranking algorithm which however, incurs two major challenges: 1) The ranking model often imposes pairwise constraints between each proposal, rendering the problem away from an efficient training/testing phase; 2) Linear kernels are utilized due to the computational and memory bottleneck of training a kernelized model. In this paper, we remedy these two issues by suggesting a kernelized partial ranking model . In particular, we demonstrate that i) our partial ranking model reduces the number of constraints from O ( n 2 ) to O ( nk ) where n is the number of all potential proposals for an image but we are only interested in top- k of them that has the largest overlap with the ground truth; ii) we permit non-linear kernels in our model which is often superior to the linear classifier in terms of accuracy. For the sake of mitigating the computational and memory issues, we introduce a consistent weighted sampling (CWS) paradigm that approximates the non-linear kernel as well as facilitates an efficient learning. In fact, as we will show, training a linear CWS model amounts to learning a kernelized model. Extensive experiments demonstrate that equipped with the non-linear kernel and the partial ranking algorithm, recall at top- k proposals can be substantially improved.