Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks

TL;DR

This paper introduces a novel cyclic fuse-and-refine module for neural networks that enhances multispectral object detection by effectively combining visible and infrared data, leading to improved detection accuracy.

Contribution

The paper presents a new fusion module that cyclically refines multispectral features, demonstrating superior performance over existing methods on challenging datasets.

Findings

Improved detection accuracy on multispectral datasets.

Effective fusion of visible and infrared features.

Outperforms state-of-the-art multispectral detection methods.

Abstract

Multispectral images (e.g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e.g. day/night outdoor scenes). To effectively use the different spectra, the main technical problem resides in the information fusion process. In this paper, we propose a new halfway feature fusion method for neural networks that leverages the complementary/consistency balance existing in multispectral features by adding to the network architecture, a particular module that cyclically fuses and refines each spectral feature. We evaluate the effectiveness of our fusion method on two challenging multispectral datasets for object detection. Our results show that implementing our Cyclic Fuse-and-Refine module in any network improves the performance on both datasets compared to other state-of-the-art multispectral object detection methods.