将异常检测融入YOLO，提升红外小目标探测的抗干扰能力。
Anomaly-Aware YOLO: A Frugal yet Robust Approach to Infrared Small Target Detection
- 用统计异常检测识别背景中的罕见目标，抑制误报
- 在有限数据和噪声环境下仍保持高鲁棒性，准确率超基准模型
- 仅修改检测头，适配轻量级模型，适合资源受限场景
红外小目标检测（IRSTD）在国防应用中极具挑战，复杂背景与微小目标尺寸常导致传统检测器误报频发。本文提出异常感知YOLO（AA-YOLO），在检测头中引入统计异常检测机制，将小目标视为背景中的异常模式，从而有效控制误报率。该方法在多个IRSTD基准测试中表现优异，且在训练数据有限、存在噪声及域偏移的场景下展现出显著鲁棒性。由于仅修改检测头，设计高度通用，已成功适配多种YOLO主干网络，包括轻量级模型，并可集成至实例分割任务中。其高效性与灵活性使其成为资源受限场景下的理想部署方案。代码将公开发布。
原文摘要 · Abstract (English)
Infrared Small Target Detection (IRSTD) is a challenging task in defense applications, where complex backgrounds and tiny target sizes often result in numerous false alarms using conventional object detectors. To overcome this limitation, we propose Anomaly-Aware YOLO (AA-YOLO), which integrates a statistical anomaly detection test into its detection head. By treating small targets as unexpected patterns against the background, AA-YOLO effectively controls the false alarm rate. Our approach not only achieves competitive performance on several IRSTD benchmarks, but also demonstrates remarkable robustness in scenarios with limited training data, noise, and domain shifts. Furthermore, since only the detection head is modified, our design is highly generic and has been successfully applied across various YOLO backbones, including lightweight models. It also provides promising results when integrated into an instance segmentation YOLO. This versatility makes AA-YOLO an attractive solution for real-world deployments where resources are constrained. The code will be publicly released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。