Deep Convolutional Neural Networks (CNNs) are playing important roles in state-of-the-art visual recognition. This paper focuses on modeling the spatial co-occurrence of neuron responses, which is less studied in the previous work. For this, we consider the neurons in the hidden layer as neural words, and construct a set of geometric neural phrases on top of them. The idea that grouping neural words into neural phrases is borrowed from the Bag-of-Visual-Words (BoVW) model. Next, the Geometric Neural Phrase Pooling (GNPP) algorithm is proposed to efficiently encode these neural phrases. GNPP acts as a new type of hidden layer, which punishes the isolated neuron responses after convolution, and can be inserted into a CNN model with little extra computational overhead. Experimental results show that GNPP produces significant and consistent accuracy gain in image classification.
@article{arxiv.1607.06514,
title = {Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons},
author = {Lingxi Xie and Qi Tian and John Flynn and Jingdong Wang and Alan Yuille},
journal= {arXiv preprint arXiv:1607.06514},
year = {2016}
}