Object proposal with kernelized partial ranking
نویسندگان
چکیده
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) 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 groundtruth; 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.
منابع مشابه
Semi-supervised bipartite ranking with the normalized Rayleigh coefficient
We propose a new algorithm for semi-supervised learning in the bipartite ranking framework. It is based on the maximization of a so-called normalized Rayleigh coefficient, which differs from the usual Rayleigh coefficient of Fisher’s linear discriminant in that the actual covariance matrices are used instead of the scatter matrices. We show that if the class conditional distributions are Gaussi...
متن کاملScalable, High-Quality Object Detection
Current high-quality object detection approaches use the same scheme: salience-based object proposal methods followed by post-classification using deep convolutional features. This spurred recent research in improving object proposal methods [18, 32, 15, 11, 2]. However, domain agnostic proposal generation has the principal drawback that the proposals come unranked or with very weak ranking, ma...
متن کاملAppendix: Kernelized Sorting
We compare a number of different object layout algorithms. Figure 1, 2, and 4 depict the results obtained by laying out 320 image objects into a 2D grid with Kernelized Sorting (our method), Self Organizing Map http://www.cis.hut.fi/projects/somtoolbox/, and Generative Topographic Mapping (GTM) http://www.ncrg.aston.ac.uk/GTM/. Figure 3 and 5 show the corresponding cluster members of SOM and GTM.
متن کاملKernelized Non-Euclidean Relational c-Means Algorithms
Successes with kernel-based classification methods have spawned many recent efforts to kernelize clustering algorithms for object data. We extend this idea to the relational data case by proposing kernelized forms of the non-Euclidean relational fuzzy (NERF) and hard (NERH) c-means algorithms. We show that these relational forms are dual to kernelized forms of fuzzy and hard c-means (FCM, HCM) ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Pattern Recognition
دوره 69 شماره
صفحات -
تاریخ انتشار 2017