# Pruning Distorted Images in MNIST Handwritten Digits

arXiv: https://arxiv.org/abs/2307.14343 · HTML: https://mlsanity.com/paper/2307.14343/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 59 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree](https://mlsanity.com/paper/1509.08985/) (2015)
- [No Routing Needed Between Capsules](https://mlsanity.com/paper/2001.09136/) (2020)
- [On Classification of Distorted Images with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.01924/) (2017)
- [Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures](https://mlsanity.com/paper/1608.06037/) (2016)
- [ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks](https://mlsanity.com/paper/1505.00393/) (2015)
- [APAC: Augmented PAttern Classification with Neural Networks](https://mlsanity.com/paper/1505.03229/) (2015)
- [RMDL: Random Multimodel Deep Learning for Classification](https://mlsanity.com/paper/1805.01890/) (2018)
- [Deep Convolutional Neural Networks as Generic Feature Extractors](https://mlsanity.com/paper/1710.02286/) (2017)
- [On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units](https://mlsanity.com/paper/1508.00330/) (2015)
- [Inception Recurrent Convolutional Neural Network for Object Recognition](https://mlsanity.com/paper/1704.07709/) (2017)
- [Batch-normalized Maxout Network in Network](https://mlsanity.com/paper/1511.02583/) (2015)
- [Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation](https://mlsanity.com/paper/2111.01632/) (2021)

## Abstract (arXiv)

Recognizing handwritten digits is a challenging task primarily due to the diversity of writing styles and the presence of noisy images. The widely used MNIST dataset, which is commonly employed as a benchmark for this task, includes distorted digits with irregular shapes, incomplete strokes, and varying skew in both the training and testing datasets. Consequently, these factors contribute to reduced accuracy in digit recognition. To overcome this challenge, we propose a two-stage deep learning approach. In the first stage, we create a simple neural network to identify distorted digits within the training set. This model serves to detect and filter out such distorted and ambiguous images. In the second stage, we exclude these identified images from the training dataset and proceed to retrain the model using the filtered dataset. This process aims to improve the classification accuracy and confidence levels while mitigating issues of underfitting and overfitting. Our experimental results demonstrate the effectiveness of the proposed approach, achieving an accuracy rate of over 99.5% on the testing dataset. This significant improvement showcases the potential of our method in enhancing digit classification accuracy. In our future work, we intend to explore the scalability of this approach and investigate techniques to further enhance accuracy by reducing the size of the training data.