EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917379797155840 |
|---|---|
| author | Monga, Munish Chudasama, Vishal Wasnik, Pankaj Jawahar, C. V. |
| author_facet | Monga, Munish Chudasama, Vishal Wasnik, Pankaj Jawahar, C. V. |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20985 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer Monga, Munish Chudasama, Vishal Wasnik, Pankaj Jawahar, C. V. Computer Vision and Pattern Recognition 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%. |
| title | EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20985 |