Self-Supervised Representation Learning for Document Image Classification [PDF]
IEEE Access, 2021 Supervised learning, despite being extremely effective, relies on expensive, time-consuming, and error-prone annotations. Self-supervised learning has recently emerged as a strong alternate to supervised learning in a range of different domains as ...
Shoaib Ahmed Siddiqui +2 more
doaj +3 more sources
Unsupervised Exemplar-Based Learning for Improved Document Image Classification
IEEE Access, 2019 Many recent state-of-the-art approaches for document image classification are based on supervised feature learning that requires a large amount of labeled training data.
Sherif Abuelwafa +2 more
doaj +3 more sources
Semantic Document Image Classification Based on Valuable Text Pattern [PDF]
Journal of Intelligent Procedures in Electrical Technology, 2011 Knowledge extraction from detected document image is a complex problem in the field of information technology. This problem becomes more intricate when we know, a negligible percentage of the detected document images are valuable.
Hossein Pourghassem +2 more
doaj +1 more source
The Reality of High Performing Deep Learning Models: A Case Study on Document Image Classification
IEEE AccessDeep neural networks have demonstrated exceptional performance breakthroughs in the field of document image classification; yet, there has been limited research in the field that delves into the explainability of these models. In this paper, we present a
Saifullah +3 more
doaj +2 more sources
Tsallis Mutual Information for Document Classification
Entropy, 2011 Mutual information is one of the mostly used measures for evaluating image similarity. In this paper, we investigate the application of three different Tsallis-based generalizations of mutual information to analyze the similarity between scanned ...
Màrius Vila +3 more
doaj +3 more sources
Enhancing Document Classification Through Multimodal Image-Text Classification: Insights from Fine-Tuned CLIP and Multimodal Deep Fusion [PDF]
SensorsFoundation models excel on general benchmarks but often underperform in clinical settings due to domain shift between internet-scale pretraining data and medical data. Multimodal deep learning, which jointly leverages medical images and clinical text, is
Hosam Aljuhani +2 more
doaj +2 more sources
A Multi-Modal Multilingual Benchmark for Document Image Classification [PDF]
Findings of the Association for Computational Linguistics: EMNLP 2023, 2023 Accepted to EMNLP 2023 (Findings)
Yoshinari Fujinuma +5 more
core +4 more sources
Document image and zone classification through incremental learning [PDF]
2013 IEEE International Conference on Image Processing, 2013 We present an incremental learning method for document image and zone classification. We consider an industrial context where the system faces a large variability of digitized administrative documents that become available progressively over time. Each new incoming document is segmented into physical regions (zones) which are classified according to a ...
Mohamed-Rafik Bouguelia, Abdel Belaid
exaly +2 more sources
Improving Accuracy and Speeding Up Document Image Classification Through Parallel Systems [PDF]
Lecture Notes in Computer Science, 2020 David Garcia +2 more
exaly +1 more source
Application of EfficientNet-based Transfer Learning in Image Classification of Modern Documents: Taking Shanghai Library's "Picture Gallery of Modern Chinese Literature" as an Example [PDF]
Nongye tushu qingbao xuebao, 2023 [Purpose/Significance] As important historical data, images in modern literature are increasingly valued by humanities researchers. The deep annotation of large-scale image resources has also become an important part of the construction of image data ...
YANG Min, GUO Limin
doaj +1 more source