RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization

arXiv:2404.09530v1 Announce Type: new
Abstract: Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of annotated instances, which is both expensive and time-consuming. As a result, differences between the source and target domains may significantly impact how well these models function. To solve this problem, domain adaptation approaches have been developed that use a small quantity …

abstract advances arxiv cs.ai cs.cv dataset datasets deep learning deep learning techniques detection diversity document domain domain adaptation ground-truth however instances them training truth type