Complex Layout Classification in the Wild: A Low-Resource Approach with Layout-Preserving Augmentations

2026-06-15

AI Summary

This study addresses the challenges of complex document layout classification under low-resource conditions, where limited annotations, poor image quality, and intricate structural semantics hinder performance. The authors construct a manually annotated dataset comprising eight layout categories and propose a CNN-based classification approach enhanced with a layout-preserving data augmentation strategy to improve generalization. Key innovations include a narrow anisotropic Gaussian masking technique that effectively retains critical segmentation structures and a reflection-induced label transformation that broadens the training distribution to mitigate class imbalance. Experimental results demonstrate that the proposed method significantly enhances both accuracy and robustness in page-level layout classification, even under severe annotation scarcity.

Abstract

Many digitized corpora suffer from low resources because annotations may be scarce, page scans are noisy and of poor resolution, or layouts are structurally complex in ways that negatively affect the quality of automatic transcription. Developing robust classification models for low-resource languages is inhibited by the lack of large-scale annotated data and by the frequent semantic complexity of page layouts. To this end, we have curated a complex-layout dataset, manually classified into eight distinct layout types based on their separator regions. To overcome data scarcity, we propose a novel training strategy in the form of a CNN-based classifier that employs strong, domain-aware augmentations to improve generalization. We utilize narrow anisotropic Gaussian masking to suppress incidental textual details while preserving essential separations, compelling the model to learn global geometric arrangements. Additionally, we implement reflection-induced label transformations to enrich the training distribution while maintaining label consistency across asymmetric categories. The results demonstrate that layout-specific augmentations can substantially improve page-level layout classification under severe annotation scarcity.

Problem

• low-resource
• complex layout
• page classification
• annotation scarcity
• document layout analysis

Innovation

• layout-preserving augmentation
• low-resource layout classification
• anisotropic Gaussian masking
• reflection-induced label transformation
• complex document layout