LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912801313783808 |
|---|---|
| author | Su, Yuchen Chen, Zhineng Du, Yongkun Wu, Zuxuan Xie, Hongtao Jiang, Yu-Gang |
| author_facet | Su, Yuchen Chen, Zhineng Du, Yongkun Wu, Zuxuan Xie, Hongtao Jiang, Yu-Gang |
| contents | End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains challenging. We identify the primary bottleneck as the lack of a reliable and efficient text detection method. To address this, we propose a novel parameterized text shape representation based on low-rank approximation for precise detection and a triple assignment detection head for fast inference. Specifically, unlike current data-irrelevant shape representation methods, we exploit shape correlations among labeled text boundaries to construct a robust low-rank subspace. By minimizing an $\ell_1$-norm objective, we extract orthogonal vectors that capture the intrinsic text shape from noisy annotations, enabling precise reconstruction via the linear combination of only a few basis vectors. Next, the triple assignment scheme decouples training complexity from inference speed. It utilizes a deep sparse branch to guide an ultra-lightweight inference branch, while a dense branch provides rich parallel supervision. Building upon these advancements, we integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++, capable of accurately and efficiently spotting arbitrary-shaped text. Extensive experiments on challenging benchmarks demonstrate the superiority of LRANet++ compared to state-of-the-art methods. Code is available at: https://github.com/ychensu/LRANet-PP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_05818 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting Su, Yuchen Chen, Zhineng Du, Yongkun Wu, Zuxuan Xie, Hongtao Jiang, Yu-Gang Computer Vision and Pattern Recognition End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains challenging. We identify the primary bottleneck as the lack of a reliable and efficient text detection method. To address this, we propose a novel parameterized text shape representation based on low-rank approximation for precise detection and a triple assignment detection head for fast inference. Specifically, unlike current data-irrelevant shape representation methods, we exploit shape correlations among labeled text boundaries to construct a robust low-rank subspace. By minimizing an $\ell_1$-norm objective, we extract orthogonal vectors that capture the intrinsic text shape from noisy annotations, enabling precise reconstruction via the linear combination of only a few basis vectors. Next, the triple assignment scheme decouples training complexity from inference speed. It utilizes a deep sparse branch to guide an ultra-lightweight inference branch, while a dense branch provides rich parallel supervision. Building upon these advancements, we integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++, capable of accurately and efficiently spotting arbitrary-shaped text. Extensive experiments on challenging benchmarks demonstrate the superiority of LRANet++ compared to state-of-the-art methods. Code is available at: https://github.com/ychensu/LRANet-PP. |
| title | LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.05818 |