RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization.
Avinash AnandRaj JaiswalMohit GuptaSiddhesh S. BangarPijush BhuyanNaman LalRajeev SinghRitika JhaRajiv Ratn ShahShin'ichi SatohPublished in: MMAsia (2023)
Keyphrases
- domain adaptation
- document layout
- cross domain
- labeled data
- semi supervised
- structure extraction
- sentiment classification
- transfer learning
- database
- multiple sources
- active learning
- page segmentation
- training data
- semi supervised learning
- document classification
- target domain
- co training
- document analysis
- document image analysis
- test data
- unsupervised learning
- information extraction
- pairwise
- feature space
- similarity measure