2025/12/07 by Zhao, Qiyan, Yan, Yue, Wang, Da-Han
Computer Science · #Handwritten Text Recognition Techniques #Topic Modeling #Advanced Neural Network Applications
paper · doi:10.48550/arxiv.2512.06657
In scene text detection, Transformer-based methods have addressed the global feature extraction limitations inherent in traditional convolution neural network-based methods. However, most directly rely on native Transformer attention layers as encoders without evaluating their cross-domain limitations and inherent shortcomings: forgetting important information or focusing on irrelevant representations when modeling long-range dependencies for text detection. The recently proposed state space model Mamba has demonstrated better long-range dependencies modeling through a linear complexity selection mechanism. Therefore, we propose a novel scene text detector based on Mamba that integrates the selection mechanism with attention layers, enhancing the encoder's ability to extract relevant information from long sequences. We adopt the Top_k algorithm to explicitly select key information and reduce the interference of irrelevant information in Mamba modeling. Additionally, we design a dual-scale feed-forward network and an embedding pyramid enhancement module to facilitate high-dimensional hidden state interactions and multi-scale feature fusion. Our method achieves state-of-the-art or competitive performance on various benchmarks, with F-measures of 89.7%, 89.2%, and 78.5% on CTW1500, TotalText, and ICDAR19ArT, respectively. Codes will be available.