Efficient Multi-domain Text Recognition Deep Neural Network Parameterization with Residual Adapters
Preprint
Abstract
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 requirements, this study presents a novel neural network model adept at optical character recognition (OCR) across diverse domains, leveraging the strengths of multi-task learning to improve efficiency and generalization. The model is designed to achieve rapid adaptation to new domains, maintain a compact size conducive to reduced computational resource demand, ensure high accuracy, retain knowledge from previous learning experiences, and allow for domain-specific performance improvements without the need to retrain entirely. Rigorous evaluation on open datasets has validated the model's ability to significantly lower the number of trainable parameters without sacrificing performance, indicating its potential as a scalable and adaptable solution in the field of computer vision, particularly for applications in optical text recognition.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Vision Transformer Adapters for Generalizable Multitask Learning2023
- Progressive learning: A deep learning framework for continual learningNeural Networks, 2020
- Continual lifelong learning with neural networks: A reviewNeural Networks, 2019
- High Performance Visual Tracking with Siamese Region Proposal Network2018
- Efficient Parametrization of Multi-domain Deep Neural Networks2018
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- Identity Mappings in Deep Residual Networks2016
- Deep learningNature, 2015
- Adaptive classifiers for multisource OCRInternational Journal on Document Analysis and Recognition (IJDAR), 2003
- Catastrophic forgetting in connectionist networksTrends in Cognitive Sciences, 1999