论文标题
是否已经使无限制的手写文本识别过时了卷积？
Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?
论文作者
论文摘要
对于深层神经网络而言，无约束的手写文本识别仍然是一个重要的挑战。在过去的几年中，经常性网络以及更具体的长期短期内存网络已经在该领域实现了最新的性能。然而，它们是由大量可训练的参数制成的，训练复发的神经网络不支持并行性。这直接影响了此类架构的训练时间，也直接影响探索各种体系结构所需的时间。最近，已经提出了无复发的体系结构，例如具有门控机制的完全卷积网络，这是一种可能实现竞争结果的替代性。在本文中，我们探讨了卷积体系结构，并将它们与CNN+BLSTM基线进行了比较。我们提出了一项有关使用Rimes数据集在离线手写识别任务上的不同体系结构的实验研究，以及它的修改版本，其中包括用打印网格的笔记本背景增强图像。
Unconstrained handwritten text recognition remains an important challenge for deep neural networks. These last years, recurrent networks and more specifically Long Short-Term Memory networks have achieved state-of-the-art performance in this field. Nevertheless, they are made of a large number of trainable parameters and training recurrent neural networks does not support parallelism. This has a direct influence on the training time of such architectures, with also a direct consequence on the time required to explore various architectures. Recently, recurrence-free architectures such as Fully Convolutional Networks with gated mechanisms have been proposed as one possible alternative achieving competitive results. In this paper, we explore convolutional architectures and compare them to a CNN+BLSTM baseline. We propose an experimental study regarding different architectures on an offline handwriting recognition task using the RIMES dataset, and a modified version of it that consists of augmenting the images with notebook backgrounds that are printed grids.
