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

2020/05/24 by Yang Liu, Liu, Yang, Hai-Long Tu +8 · 1 citation
Computer Science · Engineering · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Digital Imaging for Blood Diseases #Embedding #Engineering #FOS: Computer and information sciences #Image (mathematics) #MNIST database #Machine Learning (cs.LG) #Noise (video) #Pattern recognition (psychology) #Pixel #Task (project management) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.2005.11679

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2020/05/24 · openalex created_date 2020/05/29 · arxiv created 2022/01/14 · arxiv updated 2022/01/17 · openalex updated_date 2026/07/28

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.

Citations

• The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
• word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
• ImageNet classification with deep convolutional neural networks
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Comparing deep neural networks against humans: object recognition when the signal gets weaker
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• Recent advances in convolutional neural networks

Cited by

• Dual-coding contrastive learning based on ConvNeXt and ViT models for morphological classification of galaxies in COSMOS-Web

Related

• Noise robust neural network architecture
• Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup Table
• LAN: Learning to Adapt Noise for Image Denoising
• CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise
• Conditional Image Generation with PixelCNN Decoders