paper-with-me

Papers

Second-order Convolutional Neural Networks

2017-03-20 · Kaicheng Yu, Mathieu Salzmann

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.

📄 PDF Abstract BibTeX arXiv:1703.06817

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

FASON: First and Second Order Information Fusion Network for Texture Recognition

2017-07-01 · CVPR 2017 7 · Xiyang Dai, Joe Yue-Hei Ng, Larry S. Davis

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

2018-11-29 · CVPR 2019 6 · Zilin Gao, Jiangtao Xie, Qilong Wang, Peihua Li

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 Recognition

SoGCN: Second-Order Graph Convolutional Networks

2021-10-14 · Peihao Wang, Yuehao Wang, Hua Lin, Jianbo Shi

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 Answering

A comparison of second-order methods for deep convolutional neural networks

2018-01-01 · ICLR 2018 1 · Patrick H. Chen, Cho-Jui Hsieh

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 methods

Categorical Mixture Models on VGGNet activations

2018-03-06 · Sean Billings

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