mlsanityData to 7 Oct 2026

Efficient Multi-domain Text Recognition Deep Neural Network Parameterization with Residual Adapters

arXiv 2401.00971 ↗First posted 1 Jan 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 1 Jan 2024.

Builds on

30 of 43 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2016Progressive Neural Networkscited by 1,332
  7. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  9. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  10. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  11. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  12. 2017Learning multiple visual domains with residual adapterscited by 553
18 more
  1. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  2. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  3. 2020AdapterHub: A Framework for Adapting Transformerscited by 441
  4. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  5. 2023LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 317
  6. 2020AdapterDrop: On the Efficiency of Adapters in Transformerscited by 223
  7. 2018Efficient parametrization of multi-domain deep neural networkscited by 168
  8. 2021UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuningcited by 162
  9. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  10. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  11. 2020Memory Efficient Class-Incremental Learning for Image Classificationcited by 50
  12. 2020Multi-Source Domain Adaptation for Text Classification via DistanceNet-Banditscited by 30
  13. 2023Vision Transformer Adapters for Generalizable Multitask Learningcited by 14
  14. 2021Cross-lingual Text Classification with Heterogeneous Graph Neural Networkcited by 12
  15. 2023FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezingcited by 8
  16. 2021Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmarkcited by 7
  17. 2022Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraintscited by 5
  18. 2022Distributionally robust and generalizable inferencecited by 3

Built on by

Not cited yet.