|Yunhe Wang||Noah’s Ark Laboratory, Huawei Technologies Co., Ltd.|
|Chang Xu||The University of Sydney|
|Chunjing XU||Huawei Technologies|
|Chao Xu||Peking University|
|Dacheng Tao||University of Technology, Sydney|
This paper introduces versatile filters to construct efficient convolutional neural network.
This paper introduces versatile filters to construct efficient convolutional neural network. Considering the demands of efficient deep learning techniques running on cost-effective hardware, a number of methods have been developed to learn compact neural networks. Most of these works aim to slim down filters in different ways, e.g., investigating small, sparse or binarized filters. In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter. These secondary filters all inherit in the primary filter without occupying more storage, but once been unfolded in computation they could significantly enhance the capability of the filter by integrating information extracted from different receptive fields. Besides spatial versatile filters, we additionally investigate versatile filters from the channel perspective. The new techniques are general to upgrade filters in existing CNNs. Experimental results on benchmark datasets and neural networks demonstrate that CNNs constructed with our versatile filters are able to achieve comparable accuracy as that of original filters, but require less memory and FLOPs.