# Meta-learning of Pooling Layers for Character Recognition

arXiv: https://arxiv.org/abs/2103.09528 · HTML: https://mlsanity.com/paper/2103.09528/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 17 Mar 2021.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Meta-Learning with Latent Embedding Optimization](https://mlsanity.com/paper/1807.05960/) (2018)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Strip Pooling: Rethinking Spatial Pooling for Scene Parsing](https://mlsanity.com/paper/2003.13328/) (2020)
- [Compact Bilinear Pooling](https://mlsanity.com/paper/1511.06062/) (2015)
- [MultiGrain: a unified image embedding for classes and instances](https://mlsanity.com/paper/1902.05509/) (2019)
- [Meta-Learning Symmetries by Reparameterization](https://mlsanity.com/paper/2007.02933/) (2020)
- [Unsupervised Meta-Learning For Few-Shot Image Classification](https://mlsanity.com/paper/1811.11819/) (2018)
- [Meta-Learning of Neural Architectures for Few-Shot Learning](https://mlsanity.com/paper/1911.11090/) (2019)
- [Global Second-order Pooling Convolutional Networks](https://mlsanity.com/paper/1811.12006/) (2018)
- [Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization](https://mlsanity.com/paper/1712.01034/) (2017)
- [The Omniglot challenge: a 3-year progress report](https://mlsanity.com/paper/1902.03477/) (2019)
- [Fractional Max-Pooling](https://mlsanity.com/paper/1412.6071/) (2014)
- [Learning to Forget for Meta-Learning](https://mlsanity.com/paper/1906.05895/) (2019)
- [LIP: Local Importance-based Pooling](https://mlsanity.com/paper/1908.04156/) (2019)
- [Detail-Preserving Pooling in Deep Networks](https://mlsanity.com/paper/1804.04076/) (2018)
- [Variational Metric Scaling for Metric-Based Meta-Learning](https://mlsanity.com/paper/1912.11809/) (2019)
- [Multi-scale Location-aware Kernel Representation for Object Detection](https://mlsanity.com/paper/1804.00428/) (2018)
- [A pooling based scene text proposal technique for scene text reading in the wild](https://mlsanity.com/paper/1811.10003/) (2018)
- [Regularized Pooling](https://mlsanity.com/paper/2005.03709/) (2020)

## Built on by (most cited first, 3 of 3)

- [DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning](https://mlsanity.com/paper/2501.12898/) (2025)
- [MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning](https://mlsanity.com/paper/2505.20513/) (2025)
- [Progressive Meta-Pooling Learning for Lightweight Image Classification Model](https://mlsanity.com/paper/2301.10038/) (2023)

## Abstract (arXiv)

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.