arxivst stuff from arxiv that you should probably bookmark

Is Second-order Information Helpful for Large-scale Visual Recognition?

Abstract · Mar 23, 2017 12:55 ·


Arxiv Abstract

  • Peihua Li
  • Jiangtao Xie
  • Qilong Wang
  • Wangmeng Zuo

By stacking deeper layers of convolutions and nonlinearity, convolutional networks (ConvNets) effectively learn from low-level to high-level features and discriminative representations. Since the end goal of large-scale recognition is to delineate the complex boundaries of thousands of classes in a large-dimensional space, adequate exploration of feature distributions is important for realizing full potentials of ConvNets. However, state-of-the-art works concentrate only on deeper or wider architecture design, while rarely exploring feature statistics higher than first-order. We take a step towards addressing this problem. Our method consists in covariance pooling, instead of the most commonly used first-order pooling, of high-level convolutional features. The main challenges involved are robust covariance estimation given a small sample of large-dimensional features and usage of the manifold structure of covariance matrices. To address these challenges, we present a Matrix Power Normalized Covariance (MPN-COV) method. We develop the forward and backward propagation formulas regarding the nonlinear matrix functions such that MPN-COV can be trained end-to-end. In addition, we analyze both qualitatively and quantitatively its advantage over the widely used Log-Euclidean metric. On the ImageNet 2012 validation set, by combining MPN-COV we achieve over 4%, 3% and 2.5% gains for AlexNet, VGG-M and VGG-16, respectively; integration of MPN-COV into 50-layer ResNet outperforms ResNet-101 and is comparable to ResNet-152, both of which use first-order, global average pooling.

Read the paper (pdf) »