A conditional GAN-based approach for enhancing transfer learning performance in few-shot HCR tasks

Abstract

Supervised learning with the restriction of a few existing training samples is called Few-Shot Learning. FSL is a subarea that puts deep learning performance in a gap, as building robust deep networks requires big training data. Using transfer learning in FSL tasks is an acceptable way to avoid the challenge of building new deep models from scratch. Transfer learning methodology considers borrowing the architecture and parameters of a previously trained model on a large-scale dataset and fine-tuning it for low-data target tasks. But practically, fine-tuning pretrained models in target FSL tasks suffers from overfitting. The few existing samples are not enough to correctly adjust the pretrained model’s parameters to provide the best fit for the target task. In this study, we consider mitigating the overfitting problem when applying transfer learning in few-shot Handwritten Character Recognition (HCR) tasks. A data augmentation approach based on Conditional Generative Adversarial Networks is introduced. CGAN is a generative model that can create artificial instances that appear more real and indistinguishable from the original samples. CGAN helps generate extra samples that hold the possible variations of human handwriting instead of applying traditional image transformations. These transformations are low-level, data-independent operations, and only produce augmented samples with limited diversity. The introduced approach was evaluated in fine-tuning the three pretrained models: AlexNet, VGG-16, and GoogleNet. The results show that the samples generated by CGAN can enhance transfer learning performance in few-shot HCR tasks. This is by achieving model fine-tuning with fewer epochs and by increasing the model’s $$F1-score$$ F 1 - s c o r e and decreasing the Generalization Error $$(E_{test})$$ ( E test ) .

Generative Adversarial Network for Real‐Time Flash Drought Monitoring: A Deep Learning Study

“…Choosing an appropriate loss function is an essential aspect when creating a GAN model consisting of two deep learning models operating together in a competitive manner (Elaraby et al., 2022). We compare the performance of the networks with different loss functions to identify the most effective loss function.…”

“…To address this, Conditional GANs (CGANs) were proposed. The main idea behind CGANs is to provide both the generator and the discriminator with additional conditional information, usually in the form of a label or some other kind of auxiliary data (Elaraby et al., 2022). Figure 1 presents a general architecture for a GAN and a CGAN.…”

Incremental Recognition of Multi-Style Tibetan Character Based on Transfer Learning

“…For the recognition of languages with simple character structures, Elaraby et al [17]. employed the pre-trained DarkNet-53 model for Braille recognition, successfully completing the Braille recognition task.…”

Improving Bert Model Accuracy for Uni-modal Aspect-Based Sentiment Analysis Task

“…To combat overfitting, we used the K-fold cross-validation approach. This method involves dividing the data into K similarly sized "folds," training the model on K-1 folds, and then testing it on the residual fold [10]. The process is repeated K times to get an overall assessment of the model's performance, with each fold serving as the test set once.…”