Reduce, reuse & recycle: Efficiently solving multi-label MRFs
نویسندگان
چکیده
In this paper, we present novel techniques that improve the computational and memory efficiency of algorithms for solving multi-label energy functions arising from discrete MRFs or CRFs. These methods are motivated by the observations that the performance of minimization algorithms depends on: (a) the initialization used for the primal and dual variables; and (b) the number of primal variables involved in the energy function. Our first method (dynamic αexpansion) works by ‘recycling’ results from previous problem instances. The second method simplifies the energy function by ‘reducing’ the number of unknown variables, and can also be used to generate a good initialization for the dynamic α-expansion algorithm by ‘reusing’ dual variables. We test the performance of our methods on energy functions encountered in the problems of stereo matching, and colour and object based segmentation. Experimental results show that our methods achieve a substantial improvement in the performance of α-expansion, as well as other popular algorithms such as sequential tree-reweighted message passing, and max-product belief propagation. In most cases we achieve a 10-15 times speed-up in the computation time. Our modified α-expansion algorithm provides similar performance to Fast-PD [15]. However, it is much simpler and can be made orders of magnitude faster by using the initialization schemes proposed in the paper. †
منابع مشابه
Mutilabel MRFs with Label Adjacency Constraint: Globally Optimal Solutions and Applications
This work addresses the problem of optimally solving Markov Random Fields(MRFs) in which labels obey a certain topology constraint. Utilizing prior information, such as domain knowledge about the appearance, shape, or spatial configuration of objects in a scene can greatly improve the accuracy of segmentation algorithms in the presence of noise, clutter, and occlusion. Nowhere is this more evid...
متن کاملA fast, massively parallel solver for large, irregular pairwise Markov random fields
Given the increasing availability of high-resolution input data, today’s computer vision problems tend to grow beyond what has been considered tractable in the past. This is especially true for Markov Random Fields (MRFs), which have expanded beyond millions of variables with thousands of labels. Such MRFs pose new challenges for inference, requiring massively parallel solvers that can cope wit...
متن کاملFastLCD: Fast Label Coordinate Descent for the Efficient Optimization of 2D Label MRFs
Recently, MRFs with two-dimensional (2D) labels have proved useful to many applications, such as image matching and optical flow estimation. Due to the huge 2D label set in these problems, existing optimization algorithms tend to be slow for the inference of 2D label MRFs, and this greatly limits the practical use of 2D label MRFs. To solve the problem, this paper presents an efficient algorith...
متن کاملDesigning a seamless learning environment to learn reduce, reuse and recycle in environmental education
This article explores the design of a seamless learning environment and activities for environmental education using mobile, wireless, and online technologies in Singapore primary schools. The learning environment and activities were designed to help students learn about environmental issues, specifically reduce, reuse and recycle (3Rs), and apply such understanding to practice. By seamless, we...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008