Applications of the Streaming Networks

TL;DR

Streaming Networks (STnets) are a versatile convolutional neural network family capable of accurately classifying noisy and transformed images, including Gaussian noise, fog, snow, and low-light conditions, demonstrating their robustness across diverse scenarios.

Contribution

The paper introduces Hybrid STnets and extends the application of STnets to new noise types and image conditions, showcasing their universality in noisy image classification.

Findings

High accuracy classification of noisy images from Cifar10 with Gaussian noise, fog, snow.

Effective classification of low-light images from Carvana dataset.

Introduction of Hybrid STnets as a new variant.

Abstract

Most recently Streaming Networks (STnets) have been introduced as a mechanism of robust noise-corrupted images classification. STnets is a family of convolutional neural networks, which consists of multiple neural networks (streams), which have different inputs and their outputs are concatenated and fed into a single joint classifier. The original paper has illustrated how STnets can successfully classify images from Cifar10, EuroSat and UCmerced datasets, when images were corrupted with various levels of random zero noise. In this paper, we demonstrate that STnets are capable of high accuracy classification of images corrupted with Gaussian noise, fog, snow, etc. (Cifar10 corrupted dataset) and low light images (subset of Carvana dataset). We also introduce a new type of STnets called Hybrid STnets. Thus, we illustrate that STnets is a universal tool of image classification when original training dataset is corrupted with noise or other transformations, which lead to information loss from original images.