DATa: Domain Adaptation-aided deep Table detection using visual–lexical representations

Hyebin Kwon, Joungbin An, Dongwoo Lee, Won Yong Shin

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Article number109946
JournalKnowledge-Based Systems
Publication statusPublished - 2022 Dec 22

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF), Republic of Korea Grant by the Korean Government through MSIT under Grants 2021R1A2C3004345 and 2021R1A4A1029780 and in part by the Institute of Information and Communications Technology Planning and Evaluation (IITP), Republic of Korea Grant by the Korean Government through MSIT (6G Post-MAC—POsitioning and Spectrum-Aware intelligenT MAC for Computing and Communication Convergence) under Grant 2021-0-00347 .

Publisher Copyright:
© 2022 Elsevier B.V.

All Science Journal Classification (ASJC) codes

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence


Dive into the research topics of 'DATa: Domain Adaptation-aided deep Table detection using visual–lexical representations'. Together they form a unique fingerprint.

Cite this