SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition. (arXiv:2202.11949v1 [cs.CV])

Training recognition models with synthetic images have achieved remarkable
results in text recognition. However, recognizing text from real-world images
still faces challenges due to the domain shift between synthetic and real-world
text images. One of the strategies to eliminate the domain difference without
manual annotation is unsupervised domain adaptation (UDA). Due to the
characteristic of sequential labeling tasks, most popular UDA methods cannot be
directly applied to text recognition. To tackle this problem, we proposed a UDA
method with minimizing …

arxiv cv entropy image image recognition smile text