论文标题
合成到真实的无监督域适应野外场景文本检测
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
论文作者
论文摘要
基于深度学习的场景文本检测可以实现可取的性能，并采用足够的标记培训数据。但是，手动标签是耗时且费力的。在极端情况下，相应的注释数据不可用。利用合成数据是一个非常有前途的解决方案，除了合成数据集和实际数据集之间的域分布不匹配。为了解决严重的域分布不匹配，我们提出了一种用于场景文本检测的合成到现实域的适应方法，该方法将知识从合成数据（源域）转移到真实数据（目标域）。在本文中，引入了用于域自适应场景文本检测的文本自我训练（TST）方法和对抗文本实例对齐（ATA）。 ATA通过以对抗性方式训练域分类器来帮助网络学习域不变特征。 TST减少了不准确的伪标签的假阳性〜（fps）和假阴性〜（fns）的不利影响。从合成到现场的场景调整时，两个组件对改善场景文本探测器的性能有积极影响。我们通过从合成文本转移到ICDAR2015，ICDAR2013来评估所提出的方法。结果证明了提出的方法的有效性，提高了10％，这对于域自适应场景文本检测具有重要的探索意义。代码可从https://github.com/weijiawu/syntoreal_std获得
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, VISD to ICDAR2015, ICDAR2013. The results demonstrate the effectiveness of the proposed method with up to 10% improvement, which has important exploration significance for domain adaptive scene text detection. Code is available at https://github.com/weijiawu/SyntoReal_STD
