Self-Supervised Representation Learning on Document Images
This work analyses the impact of self-supervised pre-training on document images in the context of document image classification. While previous approaches explore the effect of self-supervision on natural images, we show that patch-based pre-training performs poorly on document images because of their different structural properties and poor intra-sample semantic information. We propose two context-aware alternatives to improve performance on the Tobacco-3482 image classification task. We also propose a novel method for self-supervision, which makes use of the inherent multi-modality of documents (image and text), which performs better than other popular self-supervised methods, including supervised ImageNet pre-training, on document image classification scenarios with a limited amount of data.
Code (0)
등록된 구현이 없습니다.
Tasks
Classificationdocument-image-classificationDocument Image ClassificationGeneral Classificationimage-classificationImage ClassificationRepresentation LearningSimilar Papers 제목 키워드 기반
DocMAE: Document Image Rectification via Self-supervised Representation Learning
Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored. In this paper, we present DocMAE, a novel self-supervised fra…
Representation LearningSelf-Supervised LearningRegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild
Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those pro…
Representation LearningSelf-Supervised LearningTable RecognitionLacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription. After supervised fine-tuning of our pre-trained enc…
Language ModelingLanguage ModellingLacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription
We present a self-supervised pre-training approach for learning rich visual language representations for both handwritten and printed historical document transcription. After supervised fine-tuning of our pre-trained enc…
Language ModelingLanguage ModellingSelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visu…
Document Layout Analysisobject-detectionObject Detection