Explore Faster Localization Learning For Scene Text Detection
This addresses the need for faster and more efficient text detection in computer vision applications, though it appears incremental as it builds on existing transformer and Fourier descriptor methods.
The paper tackles the problem of slow training in scene text detection by proposing FANet, a network that achieves state-of-the-art performance with fewer training epochs and no pre-training, as demonstrated on datasets like MSRATD500, CTW1500, and TotalText.
Generally pre-training and long-time training computation are necessary for obtaining a good-performance text detector based on deep networks. In this paper, we present a new scene text detection network (called FANet) with a Fast convergence speed and Accurate text localization. The proposed FANet is an end-to-end text detector based on transformer feature learning and normalized Fourier descriptor modeling, where the Fourier Descriptor Proposal Network and Iterative Text Decoding Network are designed to efficiently and accurately identify text proposals. Additionally, a Dense Matching Strategy and a well-designed loss function are also proposed for optimizing the network performance. Extensive experiments are carried out to demonstrate that the proposed FANet can achieve the SOTA performance with fewer training epochs and no pre-training. When we introduce additional data for pre-training, the proposed FANet can achieve SOTA performance on MSRATD500, CTW1500 and TotalText. The ablation experiments also verify the effectiveness of our contributions.