Can I read Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild on EtoBox?

Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild by Wu, Weijia; Lu, Ning; Xie, Enze is a scholarly article available to read on EtoBox.

What is Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild about?

Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are unavailable. Exploiting synthetic data is a very promising solution except for domain distribution mismatches between synthetic datasets and real datasets. To address the severe domain distribution mismatch, we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data (target domain). In this paper, a text self-training (TST) method and adversarial text instance alignment (ATA) for domain adaptive scene text detection are introduced. ATA helps the network learn domain-invariant features by training a domain classifier in an adversarial manner. TST diminishes the adverse effects of false positives~(FPs) and false negatives~(FNs) from inaccurate pseudo-labels. Two components have positive effects on improving the performance of scene text detectors when adapting from synthetic-to-real scenes. We evaluate the proposed method by transferring from SynthText, VIS

Author

Wu, Weijia; Lu, Ning; Xie, Enze

Published

2020

Language

EN