Second-order Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have been successfully applied to many computer vision tasks, such as image classification. By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image. In the past, however, second-order statistics computed from handcrafted features, e.g., covariances, have proven highly effective in diverse recognition tasks. In this paper, we introduce a novel class of CNNs that exploit second-order statistics. To this end, we design a series of new layers that (i) extract a covariance matrix from convolutional activations, (ii) compute a parametric, second-order transformation of a matrix, and (iii) perform a parametric vectorization of a matrix. These operations can be assembled to form a Covariance Descriptor Unit (CDU), which replaces the fully-connected layers of standard CNNs. Our experiments demonstrate the benefits of our new architecture, which outperform the first-order CNNs, while relying on up to 90% fewer parameters.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationSimilar Papers 제목 키워드 기반
FASON: First and Second Order Information Fusion Network for Texture Recognition
Deep networks have shown impressive performance on many computer vision tasks. Recently, deep convolutional neural networks (CNNs) have been used to learn discriminative texture representations. One of the most successfu…
Global Second-order Pooling Convolutional Networks
Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks. As the primary goal of the ConvNets is to characterize complex boundaries of thousands of classes …
Object RecognitionSoGCN: Second-Order Graph Convolutional Networks
Graph Convolutional Networks (GCN) with multi-hop aggregation is more expressive than one-hop GCN but suffers from higher model complexity. Finding the shortest aggregation range that achieves comparable expressiveness a…
Graph ClassificationGraph RegressionNode ClassificationOpen-Ended Question AnsweringA comparison of second-order methods for deep convolutional neural networks
Despite many second-order methods have been proposed to train neural networks, most of the results were done on smaller single layer fully connected networks, so we still cannot conclude whether it's useful in training d…
Second-order methodsCategorical Mixture Models on VGGNet activations
In this project, I use unsupervised learning techniques in order to cluster a set of yelp restaurant photos under meaningful topics. In order to do this, I extract layer activations from a pre-trained implementation of t…
Object Recognition