Applications of the Streaming Networks
This work addresses robust image classification under various noise and transformation conditions, but it is incremental as it extends an existing method to new types of corruption.
The paper demonstrates that Streaming Networks (STnets) achieve high accuracy in classifying images corrupted by Gaussian noise, fog, snow, and low-light conditions, using datasets like Cifar10 corrupted and a subset of Carvana, and introduces Hybrid STnets as a variant.
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.