Multidomain Document Layout Understanding using Few Shot Object Detection
This addresses the challenge of reducing data requirements for document layout analysis, making it more accessible for various domains, though it is incremental in its method.
The paper tackled the problem of multidomain document layout understanding by using a few-shot object detection approach, achieving effective generalization across domains with as few as 10 training documents per domain.
We try to address the problem of document layout understanding using a simple algorithm which generalizes across multiple domains while training on just few examples per domain. We approach this problem via supervised object detection method and propose a methodology to overcome the requirement of large datasets. We use the concept of transfer learning by pre-training our object detector on a simple artificial (source) dataset and fine-tuning it on a tiny domain specific (target) dataset. We show that this methodology works for multiple domains with training samples as less as 10 documents. We demonstrate the effect of each component of the methodology in the end result and show the superiority of this methodology over simple object detectors.