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 in a high-dimensional space, it is critical to learn higher-order representations for enhancing non-linear modeling capability. Recently, Global Second-order Pooling (GSoP), plugged at the end of networks, has attracted increasing attentions, achieving much better performance than classical, first-order networks in a variety of vision tasks. However, how to effectively introduce higher-order representation in earlier layers for improving non-linear capability of ConvNets is still an open problem. In this paper, we propose a novel network model introducing GSoP across from lower to higher layers for exploiting holistic image information throughout a network. Given an input 3D tensor outputted by some previous convolutional layer, we perform GSoP to obtain a covariance matrix which, after nonlinear transformation, is used for tensor scaling along channel dimension. Similarly, we can perform GSoP along spatial dimension for tensor scaling as well. In this way, we can make full use of the second-order statistics of the holistic image throughout a network. The proposed networks are thoroughly evaluated on large-scale ImageNet-1K, and experiments have shown that they outperform non-trivially the counterparts while achieving state-of-the-art results.
By stacking layers of convolution and nonlinearity, convolutional networks (ConvNets) effectively learn from lowlevel to high-level features and discriminative representations. ...
This paper describes a generalisation of the unscented transformation (UT) which allows sigma points to be scaled to an arbitrary dimension. The UT is a method for predicting me...
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we ...
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised...
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance. However, most of the e...
Social media, news, blog, policy document mentions