Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
This work addresses the challenge of generalizing text spotting to noisy, multi-domain real-world environments, such as underwater scenes, which is incremental by building on existing methods with a new benchmark and baseline.
The paper tackles the problem of domain-agnostic scene text spotting by training models on multi-domain data to generalize to target domains, presenting the Under-Water Text (UWT) benchmark and the DA-TextSpotter model, which achieves comparable or superior performance in accuracy and efficiency on regular and arbitrary-shaped text benchmarks.
When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system. However, existing state-of-the-art methods employ pretraining and fine-tuning strategies on natural scene datasets, which do not exploit the feature interaction across other complex domains. In this work, we explore and investigate the problem of domain-agnostic scene text spotting, i.e., training a model on multi-domain source data such that it can directly generalize to target domains rather than being specialized for a specific domain or scenario. In this regard, we present the community a text spotting validation benchmark called Under-Water Text (UWT) for noisy underwater scenes to establish an important case study. Moreover, we also design an efficient super-resolution based end-to-end transformer baseline called DA-TextSpotter which achieves comparable or superior performance over existing text spotting architectures for both regular and arbitrary-shaped scene text spotting benchmarks in terms of both accuracy and model efficiency. The dataset, code and pre-trained models will be released upon acceptance.