Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks
Convolutional Recurrent Neural Network (CRNN) is a popular network for recognizing texts in images. Advances like the variants of CRNN, such as Dense Convolutional Network with Connectionist Temporal Classification, has reduced the running time of the networks, but exposing the inner computation cost of the convolutional networks as a bottleneck. Specifically, DenseNet based frameworks use the dense blocks as the core module, but the inner features are combined in the form of concatenation in dense blocks. As a result, the number of channels of combined features delivered as the input of the layers close to the output and the relevant computational cost grows rapidly with the dense blocks getting deeper. This will severely bring heavy computational cost and restrict the depth of dense blocks. In this paper, we propose an efficient convolutional block called Fast Dense Block (FDB). To reduce the computing cost, we redefine and design the way of combining internal features of dense blocks. FDB is a convolutional block similarly as the dense block, but it applies both sum and concatenating operations to connect the inner features in blocks, which can reduce the computation cost to (1/L, 2/L), compared with the original dense block, where L is the number of layers in the dense block. Importantly, since the parameters of standard dense block and our new FDB keep consistent except the way of combining features, and their inputs and outputs have the same size and same number of channels, so FDB can be easily used to replace the original dense block in any DenseNet based framework. Based on the designed FDBs, we further propose a fast network of DenseNet to improve the text recognition performance in images.
READ FULL TEXT