7 papers
DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification
Saifullah Saifullah, Stefan Agne, Andreas Dengel +1
As black-box AI-driven decision-making systems become increasingly widespread in modern document processing workflows, improving their transparency and reliability has become criti…
DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models
Saifullah Saifullah, Stefan Agne, Andreas Dengel +1
As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of mali…
WordVIS: A Color Worth A Thousand Words
Umar Khan, Saifullah, Stefan Agne +2
Document classification is considered a critical element in automated document processing systems. In recent years multi-modal approaches have become increasingly popular for docum…
Latent Diffusion for Guided Document Table Generation
Syed Jawwad Haider Hamdani, Saifullah Saifullah, Stefan Agne +2
Obtaining annotated table structure data for complex tables is a challenging task due to the inherent diversity and complexity of real-world document layouts. The scarcity of publi…
StylusAI: Stylistic Adaptation for Robust German Handwritten Text Generation
Nauman Riaz, Saifullah Saifullah, Stefan Agne +2
In this study, we introduce StylusAI, a novel architecture leveraging diffusion models in the domain of handwriting style generation. StylusAI is specifically designed to adapt and…
DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification
Saifullah Saifullah, Stefan Agne, Andreas Dengel +1
Deep learning (DL) has revolutionized the field of document image analysis, showcasing superhuman performance across a diverse set of tasks. However, the inherent black-box nature…
PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction
Saifullah Saifullah, Stefan Agne, Andreas Dengel +1
In this paper, we introduce strategies for developing private Key Information Extraction (KIE) systems by leveraging large pretrained document foundation models in conjunction with…