2023/10/02 by Alloy Das, Das, Alloy, Sanket Biswas +9
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2310.00917
openalex publication_date 2023/10/02 · openalex created_date 2023/10/04 · openalex updated_date 2026/07/28
The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and recognition simply by pretraining on natural scene text datasets, which do not directly exploit the intermediate feature representations between multiple domains. Here, we investigate the problem of domain-adaptive scene text spotting, i.e., training a model on multi-domain source data such that it can directly adapt to target domains rather than being specialized for a specific domain or scenario. Further, we investigate a transformer baseline called Swin-TESTR to focus on solving scene-text spotting for both regular and arbitrary-shaped scene text along with an exhaustive evaluation. The results clearly demonstrate the potential of intermediate representations to achieve significant performance on text spotting benchmarks across multiple domains (e.g. language, synth-to-real, and documents). both in terms of accuracy and efficiency.