Meta-learning of Pooling Layers for Character Recognition

03/17/2021
by   Takato Otsuzuki, et al.
8

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.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 6

page 8

page 9

page 15

research
05/06/2020

Regularized Pooling

In convolutional neural networks (CNNs), pooling operations play importa...
research
11/08/2018

Alpha-Pooling for Convolutional Neural Networks

Convolutional neural networks (CNNs) have achieved remarkable performanc...
research
01/24/2023

Progressive Meta-Pooling Learning for Lightweight Image Classification Model

Practical networks for edge devices adopt shallow depth and small convol...
research
10/30/2019

Decoupling Adaptation from Modeling with Meta-Optimizers for Meta Learning

Meta-learning methods, most notably Model-Agnostic Meta-Learning or MAML...
research
05/12/2023

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

Meta-learning and other approaches to few-shot learning are widely studi...
research
05/27/2022

Attention Awareness Multiple Instance Neural Network

Multiple instance learning is qualified for many pattern recognition tas...
research
12/13/2017

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