Meta-learning of Pooling Layers for Character Recognition

TL;DR

This paper introduces a meta-learning framework for trainable pooling layers in CNNs, enabling adaptable pooling strategies that improve character recognition performance across various tasks.

Contribution

It proposes a novel meta-learning approach for parameterized pooling layers, allowing flexible and task-adaptive pooling in neural networks.

Findings

Meta-learned pooling layers enhance character recognition accuracy.

Improved performance in few-shot and noisy image recognition tasks.

Flexible pooling strategies outperform fixed pooling methods.

Abstract

In convolutional neural network-based character recognition, pooling layers play an important role in dimensionality reduction and deformation compensation. However, their kernel shapes and pooling operations are empirically predetermined; typically, a fixed-size square kernel shape and max pooling operation are used. In this paper, we propose a meta-learning framework for pooling layers. As part of our framework, a parameterized pooling layer is proposed in which the kernel shape and pooling operation are trainable using two parameters, thereby allowing flexible pooling of the input data. We also propose a meta-learning algorithm for the parameterized pooling layer, which allows us to acquire a suitable pooling layer across multiple tasks. In the experiment, we applied the proposed meta-learning framework to character recognition tasks. The results demonstrate that a pooling layer that is suitable across character recognition tasks was obtained via meta-learning, and the obtained pooling layer improved the performance of the model in both few-shot character recognition and noisy image recognition tasks.