DATa: Domain Adaptation-Aided Deep Table Detection Using Visual-Lexical Representations

TL;DR

DATa is a novel domain adaptation method for deep table detection that improves performance in target domains with limited labels by combining visual and lexical features and re-training with an augmented model.

Contribution

It introduces a new domain adaptation approach using lexical features and an augmented model to enhance deep table detection in new domains with few labels.

Findings

Outperforms existing visual-only methods in target domain detection accuracy.

Effectively reduces false positives and false negatives through confidence score optimization.

Demonstrates significant improvements on real-world benchmark datasets.

Abstract

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection with enhanced results, they often experience performance degradation when they are used for transferred domains whose table layout features might differ from the source domain in which the underlying model has been trained. To overcome this problem, we present DATa, a novel Domain Adaptation-aided deep Table detection method that guarantees satisfactory performance in a specific target domain where few trusted labels are available. To this end, we newly design lexical features and an augmented model used for re-training. More specifically, after pre-training one of state-of-the-art vision-based models as our backbone network, we re-train our augmented model, consisting of the vision-based model and the multilayer perceptron (MLP) architecture. Using new confidence scores acquired based on the trained MLP architecture as well as an initial prediction of bounding boxes and their confidence scores, we calculate each confidence score more accurately. To validate the superiority of DATa, we perform experimental evaluations by adopting a real-world benchmark dataset in a source domain and another dataset in our target domain consisting of materials science articles. Experimental results demonstrate that the proposed DATa method substantially outperforms competing methods that only utilize visual representations in the target domain. Such gains are possible owing to the capability of eliminating high false positives or false negatives according to the setting of a confidence score threshold.