Efficient and Accurate Scene Text Recognition with Cascaded-Transformers
This addresses efficiency issues for deploying STR in resource-constrained applications, but it is incremental as it builds on existing transformer methods.
The paper tackles the high computational and memory demands of vision transformers in Scene Text Recognition (STR) by introducing a cascaded-transformers structure that progressively reduces token size, achieving comparable accuracy (e.g., 92.77 to 92.68) while halving computational complexity.
In recent years, vision transformers with text decoder have demonstrated remarkable performance on Scene Text Recognition (STR) due to their ability to capture long-range dependencies and contextual relationships with high learning capacity. However, the computational and memory demands of these models are significant, limiting their deployment in resource-constrained applications. To address this challenge, we propose an efficient and accurate STR system. Specifically, we focus on improving the efficiency of encoder models by introducing a cascaded-transformers structure. This structure progressively reduces the vision token size during the encoding step, effectively eliminating redundant tokens and reducing computational cost. Our experimental results confirm that our STR system achieves comparable performance to state-of-the-art baselines while substantially decreasing computational requirements. In particular, for large-models, the accuracy remains same, 92.77 to 92.68, while computational complexity is almost halved with our structure.