Complexity · 2019 · 32 citations · 30 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingDeep LearningLoss FunctionOptical Character RecognitionPattern RecognitionRepresentation LearningCharacter ClassificationChinese Character RecognitionClass Imbalance LearningConnectionist Temporal ClassificationDeep Learning-based ClassificationFocal LossTemporal ClassificationTraining
In this paper, we propose a novel deep model for unbalanced distribution Character Recognition by employing focal loss based connectionist temporal classification (CTC) function. Previous works utilize Traditional CTC to compute prediction losses. However, some datasets may consist of extremely unbalanced samples, such as Chinese. In other words, both training and testing sets contain large amounts of low‐frequent samples. The low‐frequent samples have very limited influence on the model during training. To solve this issue, we modify the traditional CTC by fusing focal loss with it and thus make the model attend to the low‐frequent samples at training stage. In order to demonstrate the advantage of the proposed method, we conduct experiments on two types of datasets: synthetic and real image sequence datasets. The results on both datasets demonstrate that the proposed focal CTC loss function achieves desired performance on unbalanced datasets. Specifically, our method outperforms traditional CTC by 3 to 9 percentages in accuracy on average.
30
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations