End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents

arXiv:2405.04971v1 Announce Type: new
Abstract: Table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images. Although deep learning has shown remarkable progress in this realm, it typically requires an extensive dataset of labeled data for proficient training. Current CNN-based semi-supervised table detection approaches use the anchor generation process and Non-Maximum Suppression (NMS) in their detection process, limiting training efficiency. Meanwhile, transformer-based semi-supervised techniques adopted a one-to-one match strategy that provides noisy pseudo-labels, …

abstract analysis arxiv cnn cs.cv current data dataset deep learning detection document documents images object pivotal progress queries realm semi semi-supervised table table detection tables training type