CollabOD: Collaborative Multi-Backbone with Cross-scale Vision for UAV Small Object Detection

TL;DR

CollabOD is a lightweight, collaborative multi-backbone framework designed to improve small object detection in UAV imagery by preserving structural details and aligning features across scales, enhancing robustness and efficiency.

Contribution

The paper introduces CollabOD, a novel framework that explicitly preserves structural details and aligns features for improved UAV small object detection, with a lightweight design for efficiency.

Findings

Enhanced detection accuracy on UAV small object datasets.

Maintained real-time inference with reduced computational overhead.

Improved robustness and localization stability.

Abstract

Small object detection in unmanned aerial vehicle (UAV) imagery is challenging, mainly due to scale variation, structural detail degradation, and limited computational resources. In high-altitude scenarios, fine-grained features are further weakened during hierarchical downsampling and cross-scale fusion, resulting in unstable localization and reduced robustness. To address this issue, we propose CollabOD, a lightweight collaborative detection framework that explicitly preserves structural details and aligns heterogeneous feature streams before multi-scale fusion. The framework integrates Structural Detail Preservation, Cross-Path Feature Alignment, and Localization-Aware Lightweight Design strategies. From the perspectives of image processing, channel structure, and lightweight design, it optimizes the architecture of conventional UAV perception models. The proposed design enhances representation stability while maintaining efficient inference. A unified detail-aware detection head further improves regression robustness without introducing additional deployment overhead. The code is available at: https://github.com/Bai-Xuecheng/CollabOD.