Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World Object Detection (EWOD), a paradigm coupling incremental learning, domain adaptation, and unknown detection under exemplar-free constraints. To tackle EWOD, we propose EW-DETR framework that augments DETR-based detectors with three synergistic modules: Incremental LoRA Adapters for exemplar-free incremental learning under evolving domains; a Query-Norm Objectness Adapter that decouples objectness-aware features from DETR decoder queries; and Entropy-Aware Unknown Mixing for calibrated unknown detection. This framework generalises across DETR-based detectors, enabling state-of-the-art RF-DETR to operate effectively in evolving-world settings. We also introduce FOGS (Forgetting, Openness, Generalisation Score) to holistically evaluate performance across these dimensions. Extensive experiments on Pascal Series and Diverse Weather benchmarks show EW-DETR outperforms other methods, improving FOGS by 57.24%.

翻译：现实世界中的目标检测必须在不断演化的环境中运行，其中会出现新的类别、发生域偏移，并且必须将未见过的物体识别为“未知”：所有这些都要求在不访问先前数据的情况下完成。我们引入了演化世界目标检测（EWOD）这一范式，它将增量学习、域适应和未知检测在无样本约束下结合起来。为了应对EWOD，我们提出了EW-DETR框架，该框架通过三个协同模块增强了基于DETR的检测器：用于演化域下无样本增量学习的增量LoRA适配器；将目标感知特征与DETR解码器查询解耦的查询范数目标性适配器；以及用于校准未知检测的熵感知未知混合模块。该框架可推广到各种基于DETR的检测器，使最先进的RF-DETR能够在演化世界场景中有效运行。我们还引入了FOGS（遗忘度、开放度、泛化度评分）来全面评估这些维度上的性能。在Pascal Series和Diverse Weather基准测试上进行的大量实验表明，EW-DETR优于其他方法，将FOGS提高了57.24%。