Domain Adaptation Curriculum Learning for Scene Text Detection in Inclement Weather Conditions

Scene text detection has been widely studied on haze-free images with reliable ground truth annotation. However, detecting scene text in inclement weather conditions remains a major challenge due to the severe domain distribution mismatch problem. This paper introduces a domain adaptation curriculum learning method to address this problem. The scene text detector is self-trained in an easy-to-hard manner using the pseudo-labels predicted from foggy images. Thus, our method reduces the pseudo-labeling noise level. Then, a feature alignment module is introduced to help the network learn domain-invariant features by training a domain classifier. Experimental results show that our method improved significantly on both synthetic foggy data sets and natural foggy data sets, outperforming many state-of-the-art scene text detectors. (c) 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.