English
Related papers

Related papers: The OCR Quest for Generalization: Learning to reco…

200 papers

This study investigates the potential of Large Language Models (LLMs), particularly GPT-4o, for Optical Character Recognition (OCR) in low-resource scripts such as Urdu, Albanian, and Tajik, with English serving as a benchmark. Using a…

Machine Learning · Computer Science 2024-12-23 Muhammad Abdullah Sohail , Salaar Masood , Hamza Iqbal

Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Bonan Liu , Zeyu Zhang , Bingbing Meng , Han Wang , Hanshuo Zhang , Chengping Wang , Daji Ergu , Ying Cai

With the rapid development of deep learning methods, there have been many breakthroughs in the field of text classification. Models developed for this task have been shown to achieve high accuracy. However, most of these models are trained…

Machine Learning · Computer Science 2024-09-24 Yuxuan Hu , Chenwei Zhang , Min Yang , Xiaodan Liang , Chengming Li , Xiping Hu

Language models are useful adjuncts to optical models for producing accurate optical character recognition (OCR) results. One factor which limits the power of language models in this context is the existence of many specialized domains with…

Computation and Language · Computer Science 2023-08-21 Peter Garst , Reeve Ingle , Yasuhisa Fujii

Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence architecture typically used for optical character recognition (OCR)…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 Jacob Carlson , Tom Bryan , Melissa Dell

Open-set single-source domain generalization aims to use a single-source domain to learn a robust model that can be generalized to unknown target domains with both domain shifts and label shifts. The scarcity of the source domain and the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Pengkun Jiao , Na Zhao , Jingjing Chen , Yu-Gang Jiang

Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Mei Wang , Weihong Deng , Sen Su

Recent advancements in deep neural networks have markedly enhanced the performance of computer vision tasks, yet the specialized nature of these networks often necessitates extensive data and high computational power. Addressing these…

Computer Vision and Pattern Recognition · Computer Science 2024-01-03 Jiayou Chao , Wei Zhu

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

Machine Learning · Computer Science 2019-06-11 Yiying Li , Yongxin Yang , Wei Zhou , Timothy M. Hospedales

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Qi Dou , Daniel C. Castro , Konstantinos Kamnitsas , Ben Glocker

Deep learning models heavily rely on large scale annotated datasets for training. Unfortunately, datasets cannot capture the infinite variability of the real world, thus neural networks are inherently limited by the restricted visual and…

Computer Vision and Pattern Recognition · Computer Science 2020-12-17 Massimiliano Mancini

Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…

Computation and Language · Computer Science 2021-09-13 Jonas Pfeiffer , Ivan Vulić , Iryna Gurevych , Sebastian Ruder

Model transformations play a fundamental role in model-driven software development. They can be used to solve or support central tasks, such as creating models, handling model co-evolution, and model merging. In the past, various…

Software Engineering · Computer Science 2021-08-06 Christof Tinnes , Timo Kehrer , Mitchell Joblin , Uwe Hohenstein , Andreas Biesdorf , Sven Apel

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable. We study a novel and practical problem…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Yang Shu , Zhangjie Cao , Chenyu Wang , Jianmin Wang , Mingsheng Long

Open set domain recognition has got the attention in recent years. The task aims to specifically classify each sample in the practical unlabeled target domain, which consists of all known classes in the manually labeled source domain and…

Computer Vision and Pattern Recognition · Computer Science 2021-05-13 Xinxing He , Yuan Yuan , Zhiyu Jiang

Deep learning techniques have recently shown to be successful in many natural language processing tasks forming state-of-the-art systems. They require, however, a large amount of annotated data which is often missing. This paper explores…

Computation and Language · Computer Science 2020-04-23 Daniel Grießhaber , Ngoc Thang Vu , Johannes Maucher

A method is presented that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books when only small amounts of diplomatic transcriptions are available. This is achieved by…

Computer Vision and Pattern Recognition · Computer Science 2017-12-22 Christian Reul , Christoph Wick , Uwe Springmann , Frank Puppe

Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with consistency…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Mengmeng Jing , Xiantong Zhen , Jingjing Li , Cees Snoek

Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and…

Computation and Language · Computer Science 2019-06-05 Navid Rekabsaz , Nikolaos Pappas , James Henderson , Banriskhem K. Khonglah , Srikanth Madikeri

Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. In this work, we study how model architectures and pre-training objectives impact feature richness and propose a method to effectively…

Machine Learning · Computer Science 2025-04-30 Xavier Thomas , Deepti Ghadiyaram
‹ Prev 1 2 3 10 Next ›