# Solar Power Plant Detection on Multi-Spectral Satellite Imagery using Weakly-Supervised CNN with Feedback Features and m-PCNN Fusion

## TL;DR

This paper introduces a feedback CNN model with m-PCNN fusion for improved weakly-supervised detection of solar power plants in multi-spectral satellite images, inspired by primate visual perception.

## Contribution

It proposes a feedback CNN architecture with enhanced class activation mapping using m-PCNN for better localization of solar power plants.

## Key findings

- Promising results in classification accuracy.
- Effective weakly-supervised localization.
- Improved detection performance over baseline models.

## Abstract

Most of the traditional convolutional neural networks (CNNs) implements bottom-up approach (feed-forward) for image classifications. However, many scientific studies demonstrate that visual perception in primates rely on both bottom-up and top-down connections. Therefore, in this work, we propose a CNN network with feedback structure for Solar power plant detection on middle-resolution satellite images. To express the strength of the top-down connections, we introduce feedback CNN network (FB-Net) to a baseline CNN model used for solar power plant classification on multi-spectral satellite data. Moreover, we introduce a method to improve class activation mapping (CAM) to our FB-Net, which takes advantage of multi-channel pulse coupled neural network (m-PCNN) for weakly-supervised localization of the solar power plants from the features of proposed FB-Net. For the proposed FB-Net CAM with m-PCNN, experimental results demonstrated promising results on both solar-power plant image classification and detection task.