EW-DETR：通过增量低秩检测Transformer实现演化世界目标检测
EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
EW-DETR 将增量低秩适配器、查询范数对象性适配器和熵感知未知混合集成到 DETR 类检测器中，为视觉研究者在无样本增量学习、域偏移和未知目标检测耦合场景下提供了可复用的模块化方案，并提出了 FOGS 综合评价指标。
原文依据 We introduce Evolving World Object Detection (EWOD), a paradigm coupling incremental learning, domain adaptation, and unknown detection under exemplar-free constraints.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现实世界中的目标检测必须在不断演化的环境中运行，新类别出现、域发生偏移，并且必须将未见过的目标识别为未知——所有这些都无需访问先前数据。我们引入了演化世界目标检测（EWOD）范式，该范式在无样本约束下耦合了增量学习、域自适应和未知检测。为解决EWOD问题，我们提出了EW-DETR框架，通过三个协同模块增强基于DETR的检测器：用于演化域下无样本增量学习的增量低秩适配器；一个查询范数对象性适配器，将对象性感知特征与DETR解码器查询解耦；以及用于校准未知检测的熵感知未知混合。该框架可泛化到基于DETR的检测器，使最优的RF-DETR能够在演化世界设置中有效运行。我们还引入了FOGS（遗忘、开放性、泛化分数）来全面评估这些维度上的性能。在Pascal系列和多样化天气基准上的大量实验表明，EW-DETR优于其他方法，将FOGS提高了57.24%。
英文原文摘要 1134 字符
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%.