EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
This addresses the challenge of real-world object detection for applications requiring adaptation to changing conditions without prior data access, representing a novel integration of incremental learning, domain adaptation, and unknown detection.
The paper tackles the problem of object detection in evolving environments where new classes emerge and domains shift, proposing the EW-DETR framework that improves the FOGS score by 57.24% on benchmarks.
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%.