Voting in Transfer Learning System for Ground-Based Cloud Classification

TL;DR

This paper presents a transfer learning approach using pretrained deep neural networks with a voting mechanism for classifying ground-based cloud images, effectively handling unbalanced datasets and outperforming existing methods.

Contribution

It introduces a pyramidal transfer learning framework with voting for cloud classification, addressing unbalanced data and improving accuracy over state-of-the-art techniques.

Findings

Effective classification accuracy on cloud datasets

Outperforms existing state-of-the-art methods

Robustness to unbalanced datasets

Abstract

Clouds classification is a great challenge in meteorological research. The different types of clouds, currently known and present in our skies, can produce radioactive effects that impact on the variation of atmospheric conditions, with the consequent strong dominance over the earth's climate and weather. Therefore, identifying their main visual features becomes a crucial aspect. In this paper, the goal is to adopt a pretrained deep neural networks based architecture for clouds image description, and subsequently, classification. The approach is pyramidal. Proceeding from the bottom up, it partially extracts previous knowledge of deep neural networks related to original task and transfers it to the new task. The updated knowledge is integrated in a voting context to provide a classification prediction. The framework trains the neural models on unbalanced sets, a condition that makes the task even more complex, and combines the provided predictions through statistical measures. Experimental phase on different cloud image datasets is performed and results achieved show the effectiveness of the proposed approach with respect to state of the art competitors.