|
Ayan Banerjee, Sanket Biswas, Josep Llados and Umapada Pal. 2024. SemiDocSeg: Harnessing Semi-Supervised Learning for Document Layout Analysis. IJDAR.
Abstract: Document Layout Analysis (DLA) is the process of automatically identifying and categorizing the structural components (e.g. Text, Figure, Table, etc.) within a document to extract meaningful content and establish the page's layout structure. It is a crucial stage in document parsing, contributing to their comprehension. However, traditional DLA approaches often demand a significant volume of labeled training data, and the labor-intensive task of generating high-quality annotated training data poses a substantial challenge. In order to address this challenge, we proposed a semi-supervised setting that aims to perform learning on limited annotated categories by eliminating exhaustive and expensive mask annotations. The proposed setting is expected to be generalizable to novel categories as it learns the underlying positional information through a support set and class information through Co-Occurrence that can be generalized from annotated categories to novel categories. Here, we first extract features from the input image and support set with a shared multi-scale feature acquisition backbone. Then, the extracted feature representation is fed to the transformer encoder as a query. Later on, we utilize a semantic embedding network before the decoder to capture the underlying semantic relationships and similarities between different instances, enabling the model to make accurate predictions or classifications with only a limited amount of labeled data. Extensive experimentation on competitive benchmarks like PRIMA, DocLayNet, and Historical Japanese (HJ) demonstrate that this generalized setup obtains significant performance compared to the conventional supervised approach.
Keywords: Document layout analysis; Semi-supervised learning; Co-Occurrence matrix; Instance segmentation; Swin transformer
|
|
|
Josep Llados and Gemma Sanchez. 2004. Graph Matching vs. Graph Parsing in Graphics Recognition: A Combined Approach.
|
|
|
Ernest Valveny and Philippe Dosch. 2006. A general framework for the evaluation of symbol recognition methods.
|
|
|
Josep Llados and Dorothea Blostein. 2007. Special Issue on Graphics Recognition. Guest Editors.
|
|
|
Ernest Valveny and 11 others. 2006. A general framework for the evaluation of symbol recognition methods.
|
|
|
Gemma Sanchez, Alicia Fornes, Joan Mas and Josep Llados. 2007. Computer Vision Tools for Visually Impaired Children Learning.
|
|
|
Gemma Sanchez, Alicia Fornes, Joan Mas and Josep Llados. 2007. Computer Vision Tools for Visually Impaired Children Learning.
|
|
|
Ernest Valveny and Philippe Dosch. 2007. A General Framework for the Evaluation of Symbol Recognition Methods.
|
|
|
Josep Llados, J. Lopez-Krahe and D. Archambault. 2007. Special Issue on Information Technologies for Visually Impaired People. Guest Editors.
|
|
|
Josep Llados, Dimosthenis Karatzas, Joan Mas and Gemma Sanchez. 2008. A Generic Architecture for the Conversion of Document Collections into Semantically Annotated Digital Archives.
Keywords: Median Graph, Graph Embedding, Graph Matching, Structural Pattern Recognition
|
|