Fine-tuning Handwriting Recognition systems with Temporal Dropout
Not on the map. Why?
Abstract (arXiv)
This paper introduces a novel method to fine-tune handwriting recognition systems based on Recurrent Neural Networks (RNN). Long Short-Term Memory (LSTM) networks are good at modeling long sequences but they tend to overfit over time. To improve the system's ability to model sequences, we propose to drop information at random positions in the sequence. We call our approach Temporal Dropout (TD). We apply TD at the image level as well to internal network representation. We show that TD improves the results on two different datasets. Our method outperforms previous state-of-the-art on Rodrigo dataset.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 31 Jan 2021.
Builds on
15 of 24 references.
References · 15
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2016Deep Networks with Stochastic Depthcited by 973
- 2014Efficient Object Localization Using Convolutional Networkscited by 226
- 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
- 2015A Theoretically Grounded Application of Dropout in Recurrent Neural Networkscited by 161
- 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 144
- 2017Shake-Shake regularizationcited by 87
- 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
- 2013Dropout improves Recurrent Neural Networks for Handwriting Recognitioncited by 39
- 2016Recurrent Dropout without Memory Losscited by 22
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.
2 papers.