Sparse Convolutional Networks using the Permutohedral Lattice
نویسندگان
چکیده
This paper introduces an efficient, non-linear image adaptive filtering as a generalization of the standard spatial convolution of convolutional neural networks (CNNs). We build on the bilateral filtering operation, a commonly used edgeaware image processing technique. Our implementation of bilateral filters uses specialized data structures, and in this paper we demonstrate how these lead to generalizations and make the filters amendable to learning. This development enriches the convolutional operation found in CNNs, which becomes image adaptive, can process sparse input data, and produce continuous output. Our result also generalizes a class of densely connected graphical models with tractable mean field inference. It has previously been shown that mean field approximations in the subclass of models with Gaussian edge potentials reduce to a bilateral filtering operation. Here, we generalize this to the non-Gaussian case and allow highly parameterized potential functions. A diverse set of experiments validates the empirical performance and highlights the different aspects of the proposed operation.
منابع مشابه
Permutohedral Lattice CNNs
This paper presents a convolutional layer that is able to process sparse input features. As an example, for image recognition problems this allows an efficient filtering of signals that do not lie on a dense grid (like pixel position), but of more general features (such as color values). The presented algorithm makes use of the permutohedral lattice data structure. The permutohedral lattice was...
متن کاملSupplementary Material for Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
A core technical contribution of this work is the generalization of the Gaussian permutohedral lattice convolution proposed in [1] to the full non-separable case with the ability to perform backpropagation. Although, conceptually, there are minor difference between non-Gaussian and general parameterized filters, there are non-trivial practical differences in terms of the algorithmic implementat...
متن کاملSome Useful Properties of the Permutohedral Lattice for Gaussian Filtering
The rest of the paper is organized as follows: in Section 1, we give preliminary definitions of relevant terms and notation; in Section 2, we formally define the permutohedral lattice in several ways and prove useful structural properties stemming from the definition; in Section 3, we suggest criteria for picking the ideal lattice with which to perform Gaussian filtering, and present an argumen...
متن کاملEfficient Continuous Relaxations for Dense CRF Supplementary Materials
In this paper, the filter based method that we use for our experiments is the one by Adams et al. [1]. In this method, the original computation is approximated by a convolution in a higher dimensional space. The original points are associated to a set of vertices on which the convolution is performed. The considered vertices are the one from the permutohedral lattice. Krähenbühl and Koltun [2] ...
متن کاملCrop Land Change Monitoring Based on Deep Learning Algorithm Using Multi-temporal Hyperspectral Images
Change detection is done with the purpose of analyzing two or more images of a region that has been obtained at different times which is Generally one of the most important applications of satellite imagery is urban development, environmental inspection, agricultural monitoring, hazard assessment, and natural disaster. The purpose of using deep learning algorithms, in particular, convolutional ...
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:
- CoRR
دوره abs/1503.04949 شماره
صفحات -
تاریخ انتشار 2015