%0 Conference Proceedings
%T Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
%A Alloy Das
%A Sanket Biswas
%A Umapada Pal
%A Josep Llados
%B IEEE International Conference on Robotics and Automation in PACIFICO
%D 2024
%F Alloy Das2024
%O DAG
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3979), last updated on Thu, 09 May 2024 15:03:10 +0200
%X 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.
%U https://arxiv.org/abs/2310.00558
%U http://refbase.cvc.uab.es/files/DBP2023.pdf