Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception
This addresses reliability issues in safety-critical UAV perception, though it appears incremental as it builds on existing embedding-based detectors with specific enhancements.
The paper tackles the problem of open-set detection for UAV air-to-air object detection, proposing a model-agnostic framework that improves robustness against domain shifts and corrupted flight data, achieving up to a 10% relative AUROC gain over baseline methods.
Open-set detection is crucial for robust UAV autonomy in air-to-air object detection under real-world conditions. Traditional closed-set detectors degrade significantly under domain shifts and flight data corruption, posing risks to safety-critical applications. We propose a novel, model-agnostic open-set detection framework designed specifically for embedding-based detectors. The method explicitly handles unknown object rejection while maintaining robustness against corrupted flight data. It estimates semantic uncertainty via entropy modeling in the embedding space and incorporates spectral normalization and temperature scaling to enhance open-set discrimination. We validate our approach on the challenging AOT aerial benchmark and through extensive real-world flight tests. Comprehensive ablation studies demonstrate consistent improvements over baseline methods, achieving up to a 10\% relative AUROC gain compared to standard YOLO-based detectors. Additionally, we show that background rejection further strengthens robustness without compromising detection accuracy, making our solution particularly well-suited for reliable UAV perception in dynamic air-to-air environments.