让目标检测模型在不看旧数据的情况下，持续学习新类、适应环境变化并识别未知物体。
EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
- 用增量低秩适配器实现无样本记忆的持续学习，支持新类别动态加入。
- 在多个基准上提升综合性能57.24%，显著优于现有方法。
- 适合需要长期运行、环境多变的目标检测场景，如自动驾驶、智能监控。
现实世界中的目标检测需应对不断演化的环境：新类别出现、领域迁移、未知物体需被识别为“未知”，且无法访问历史数据。我们提出演化世界目标检测（EWOD）范式，融合增量学习、域自适应与无样本未知检测。为此，我们设计了基于DETR的EW-DETR框架，引入三个协同模块：用于无示例增量学习的增量低秩适配器（Incremental LoRA Adapters）；解耦对象置信度特征的查询归一化对象性适配器（Query-Norm Objectness Adapter）；以及基于熵的未知混合机制（Entropy-Aware Unknown Mixing），以实现校准的未知检测。该框架可泛化至多种DETR类检测器，使RF-DETR在演化环境中表现更优。我们还提出FOGS（遗忘、开放性、泛化性评分）综合评估指标。在Pascal Series和Diverse Weather数据集上的大量实验表明，EW-DETR优于其他方法，综合性能提升57.24%。
原文摘要 · Abstract (English)
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%.
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。