Application of Tensorized Neural Networks for Cloud Classification

TL;DR

This paper introduces a tensorized neural network approach with attention and contrastive learning for efficient cloud classification, improving model size, speed, and accuracy for weather forecasting.

Contribution

It proposes a novel tensorization method for CNN layers combined with attention and contrastive learning, enhancing efficiency and accuracy in cloud classification.

Findings

Tensorized neural networks significantly reduce model size.

Incorporating attention improves classification accuracy.

The approach enhances computational speed and data compression.

Abstract

Convolutional neural networks (CNNs) have gained widespread usage across various fields such as weather forecasting, computer vision, autonomous driving, and medical image analysis due to its exceptional ability to extract spatial information, share parameters, and learn local features. However, the practical implementation and commercialization of CNNs in these domains are hindered by challenges related to model sizes, overfitting, and computational time. To address these limitations, our study proposes a groundbreaking approach that involves tensorizing the dense layers in the CNN to reduce model size and computational time. Additionally, we incorporate attention layers into the CNN and train it using Contrastive self-supervised learning to effectively classify cloud information, which is crucial for accurate weather forecasting. We elucidate the key characteristics of tensorized neural network (TNN), including the data compression rate, accuracy, and computational speed. The results indicate how TNN change their properties under the batch size setting.