DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition
This work addresses efficiency and accuracy challenges in handwritten Chinese character recognition, an important domain-specific task, with incremental improvements through a novel training method.
The paper tackles the problem of training deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognition by proposing DropSample, a method that dynamically adjusts sample selection based on classification confidence, resulting in recognition rates of 97.33%, 97.06%, and 97.51% on benchmark datasets, significantly outperforming previous best results.
Inspired by the theory of Leitners learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural networks (DCNNs), and apply it to large-scale online handwritten Chinese character recognition (HCCR). According to the principle of DropSample, each training sample is associated with a quota function that is dynamically adjusted on the basis of the classification confidence given by the DCNN softmax output. After a learning iteration, samples with low confidence will have a higher probability of being selected as training data in the next iteration; in contrast, well-trained and well-recognized samples with very high confidence will have a lower probability of being involved in the next training iteration and can be gradually eliminated. As a result, the learning process becomes more efficient as it progresses. Furthermore, we investigate the use of domain-specific knowledge to enhance the performance of DCNN by adding a domain knowledge layer before the traditional CNN. By adopting DropSample together with different types of domain-specific knowledge, the accuracy of HCCR can be improved efficiently. Experiments on the CASIA-OLHDWB 1.0, CASIA-OLHWDB 1.1, and ICDAR 2013 online HCCR competition datasets yield outstanding recognition rates of 97.33%, 97.06%, and 97.51% respectively, all of which are significantly better than the previous best results reported in the literature.