Decoupled Attention Network for Text Recognition
This addresses alignment issues in text recognition for applications like document analysis and scene understanding, representing a novel method for a known bottleneck.
The paper tackles the alignment problem in attention-based text recognition methods by proposing a decoupled attention network (DAN) that separates alignment from historical decoding, achieving state-of-the-art performance on offline handwritten and regular/irregular scene text recognition tasks.
Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. However, most of attention methods usually suffer from serious alignment problem due to its recurrency alignment operation, where the alignment relies on historical decoding results. To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results. DAN is an effective, flexible and robust end-to-end text recognizer, which consists of three components: 1) a feature encoder that extracts visual features from the input image; 2) a convolutional alignment module that performs the alignment operation based on visual features from the encoder; and 3) a decoupled text decoder that makes final prediction by jointly using the feature map and attention maps. Experimental results show that DAN achieves state-of-the-art performance on multiple text recognition tasks, including offline handwritten text recognition and regular/irregular scene text recognition.