On Exploring and Improving Robustness of Scene Text Detection Models
This work addresses the robustness issue in scene text detection, which is critical for practical applications, but it is incremental as it builds on existing frameworks and datasets.
The authors tackled the problem of evaluating and improving the robustness of scene text detection models to various corruptions by introducing two new benchmark datasets (ICDAR2015-C and CTW1500-C) and analyzing key model components, resulting in a data-based method that significantly enhances robustness across different networks.
It is crucial to understand the robustness of text detection models with regard to extensive corruptions, since scene text detection techniques have many practical applications. For systematically exploring this problem, we propose two datasets from which to evaluate scene text detection models: ICDAR2015-C (IC15-C) and CTW1500-C (CTW-C). Our study extends the investigation of the performance and robustness of the proposed region proposal, regression and segmentation-based scene text detection frameworks. Furthermore, we perform a robustness analysis of six key components: pre-training data, backbone, feature fusion module, multi-scale predictions, representation of text instances and loss function. Finally, we present a simple yet effective data-based method to destroy the smoothness of text regions by merging background and foreground, which can significantly increase the robustness of different text detection networks. We hope that this study will provide valid data points as well as experience for future research. Benchmark, code and data will be made available at \url{https://github.com/wushilian/robust-scene-text-detection-benchmark}.