{"ID":2831929,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.06657","arxiv_id":"2512.06657","title":"TextMamba: Scene Text Detector with Mamba","abstract":"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.","short_abstract":"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 shor...","url_abs":"https://arxiv.org/abs/2512.06657","url_pdf":"https://arxiv.org/pdf/2512.06657v1","authors":"[\"Qiyan Zhao\",\"Yue Yan\",\"Da-Han Wang\"]","published":"2025-12-07T05:06:19Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false}