Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection

TL;DR

This paper introduces a novel early-fusion strategy and learning techniques to enhance the performance of efficient single-branch multispectral object detectors, addressing key challenges like information interference and domain gaps.

Contribution

It reveals the information interference problem in naive early fusion and proposes solutions including a shape-priority fusion, weakly supervised learning, and knowledge distillation.

Findings

Single-branch networks with proposed methods outperform naive approaches.

Significant performance gains while maintaining high efficiency.

Code will be publicly available for reproducibility.

Abstract

Most recent multispectral object detectors employ a two-branch structure to extract features from RGB and thermal images. While the two-branch structure achieves better performance than a single-branch structure, it overlooks inference efficiency. This conflict is increasingly aggressive, as recent works solely pursue higher performance rather than both performance and efficiency. In this paper, we address this issue by improving the performance of efficient single-branch structures. We revisit the reasons causing the performance gap between these structures. For the first time, we reveal the information interference problem in the naive early-fusion strategy adopted by previous single-branch structures. Besides, we find that the domain gap between multispectral images, and weak feature representation of the single-branch structure are also key obstacles for performance. Focusing on these three problems, we propose corresponding solutions, including a novel shape-priority early-fusion strategy, a weakly supervised learning method, and a core knowledge distillation technique. Experiments demonstrate that single-branch networks equipped with these three contributions achieve significant performance enhancements while retaining high efficiency. Our code will be available at \url{https://github.com/XueZ-phd/Efficient-RGB-T-Early-Fusion-Detection}.