Multilingual Few-shot Document Layout Analysis

Forschungsthema/Bereich
Document Analysis, Deep Learning, Computer Vision, Artifical Intelligence
Typ der Abschlussarbeit
Master
Startzeitpunkt
-
Bewerbungsschluss
31.05.2026
Dauer der Arbeit
-

Beschreibung

Document Layout Analysis (DLA) has made great strides in high-resource languages (like English and Chinese) But remains challenging for low-resource languages due to scarce labeled data. State-of-the-art models such as LayoutLM achieve strong results on English documents; however, they struggle to generalize to languages like Tamil, Urdu, or Amharic that were absent or underrepresented in training. In this thesis, we will research multilingual modeling and transfer learning to tackle DLA in low-resource languages. We will explore how multilingual document models (e.g., LayoutXLM, LayoutLMv3) pre-trained on rich-resource languages can be adapted through few-shot learning to perform layout analysis in new languages.

What you do:
● Literature research on DLA and few-shot learning.
● Dataset creation with DLA task in low-resource languages.
● Implementation of state-of-the-art methods for multilingual DLA tasks.

What we offer:
● Getting started quickly with our open-source code
● Compute resources for model training and deployment
● Experienced guidance and open discussions with other team members
● Support publishing your work at top conferences (also attending conferences in person)

Further Information:
We have further topics, such as Computer Vision, large language models (LLMs), Generative Models, Retrieval-Augmented Generation (RAG), Document Analysis and understanding, etc.

Please feel free to contact me (yufan.chen@kit.edu) with your CV and transcript of your records.

Voraussetzung

Voraussetzungen an Studierende
  • Interest in the topic of computer vision and doing task-oriented research
  • Python programming skills and knowledge of PyTorch/Tensorflow are desirable

Studiengangsbereiche
  • Ingenieurwissenschaften
    Elektrotechnik & Informationstechnik
    Geodäsie & Geoinformatik
    Informatik
    Mechatronik & Informationstechnik
    Sonstige Studienbereiche
    Remote Sensing and Geoinformatics
    Information System Engineering and Management


Betreuung

Titel, Vorname, Name
Msc., Yufan, Chen
Organisationseinheit
Computer Vision for Human-Computer Interaction Lab, Institute for Anthropomatics and Robotics (IAR)
E-Mail Adresse
yufan.chen@kit.edu
Link zur eigenen Homepage/Personenseite
Website

Bewerbung per E-Mail

Bewerbungsunterlagen
  • Lebenslauf
  • Notenauszug

E-Mail Adresse für die Bewerbung
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an yufan.chen@kit.edu


Zurück