Networks with pixels embedding: a method to improve noise resistance in images classification

TL;DR

This paper introduces a pixel embedding technique to enhance noise resistance in image classification networks, demonstrating improved performance on noisy MNIST digit images compared to conventional methods.

Contribution

The paper proposes a novel pixel embedding method that increases noise robustness in image classification networks, moving beyond traditional data augmentation techniques.

Findings

Network with PE outperforms conventional networks on noisy images.

Pixel embedding improves noise resistance in image classification.

Technique applicable to various image classification tasks.

Abstract

In the task of image classification, usually, the network is sensitive to noises. For example, an image of cat with noises might be misclassified as an ostrich. Conventionally, to overcome the problem of noises, one uses the technique of data augmentation, that is, to teach the network to distinguish noises by adding more images with noises in the training dataset. In this work, we provide a noise-resistance network in images classification by introducing a technique of pixel embedding. We test the network with pixel embedding, which is abbreviated as the network with PE, on the mnist database of handwritten digits. It shows that the network with PE outperforms the conventional network on images with noises. The technique of pixel embedding can be used in many tasks of image classification to improve noise resistance.