Meta-learning of Pooling Layers for Character Recognition

by   Takato Otsuzuki, et al.

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.


page 1

page 2

page 3

page 5

page 6

page 8

page 9

page 15


Regularized Pooling

In convolutional neural networks (CNNs), pooling operations play importa...

Alpha-Pooling for Convolutional Neural Networks

Convolutional neural networks (CNNs) have achieved remarkable performanc...

Progressive Meta-Pooling Learning for Lightweight Image Classification Model

Practical networks for edge devices adopt shallow depth and small convol...

Decoupling Adaptation from Modeling with Meta-Optimizers for Meta Learning

Meta-learning methods, most notably Model-Agnostic Meta-Learning or MAML...

Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn

Meta-learning and other approaches to few-shot learning are widely studi...

Attention Awareness Multiple Instance Neural Network

Multiple instance learning is qualified for many pattern recognition tas...

The Enhanced Hybrid MobileNet

Although complicated and deep neural network models can achieve high acc...

Please sign up or login with your details

Forgot password? Click here to reset