IEEE Transactions on Image Processing · 2021 · 34 citations · 41 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingDeep LearningPattern RecognitionTransfer LearningAdversarial Domain AdaptationDomain AdaptationSequence-to-sequence RecognitionSequential Image AnalysisText-to-image Alignment
Robust text reading is a very challenging problem, due to the distribution of text images changing significantly in real-world scenarios. One effective solution is to align the distribution between different domains by domain adaptation methods. However, we found that these methods might struggle when dealing sequence-like text images. An important reason is that conventional domain adaptation methods strive to align images as a whole, while text images consist of variable-length fine-grained character information. To address this issue, we propose a novel Adversarial Sequence-to-Sequence Domain Adaptation (ASSDA) method to learn "where to adapt" and "how to align" the sequential image. Our key idea is to mine the local regions that contain characters, and focus on aligning them across domains in an adversarial manner. Extensive text recognition experiments show the ASSDA could efficiently transfer sequence knowledge and validate the promising power towards the various domain shift in the real world applications.
41
Adversarial Discriminative Domain Adaptation
Eric Tzeng, Judy Hoffman, Kate Saenko et al. · 2017 · 5K citations
Learning Transferable Features with Deep Adaptation Networks
Mingsheng Long, Yue Cao, Jianmin Wang et al. · arXiv (Cornell University) · 2015 · 2.8K citations · Full text