Research map / Detection and segmentation / Open-set and few-shot detection
EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
Munish Monga, Vishal Chudasama, Pankaj Wasnik, C.V. Jawahar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Incremental LoRA adapters with data-aware merging (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | FSS: 7.52 -> 98.11 | Improved |
| add Incremental LoRA adapters (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | GSS: 51.49 -> 0.07 | Hurt |
| add dual LoRA without merging/SVD vs single task LoRA (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | FOGS: 37.4 -> 37.16 | No clear effect |
| add Query-Norm Objectness adapter alone (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | FOGS: 30.93 -> 31.14 | No clear effect |
| add Query-Norm Objectness adapter on top of Incremental LoRA (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | OSS: 33.53 -> 42.04 | Improved |
| add Entropy-Aware Unknown Mixing (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | OSS: 42.04 -> 78.62 | Improved |
| add Entropy-Aware Unknown Mixing (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | FSS: 97.78 -> 96.19 | Hurt |
| add Entropy-Aware Unknown Mixing (ablation) | EW-DETR (RF-DETR) · EWOD ablation: VOC -> Clipart (RF-DETR) | FOGS: 48.3 -> 61.08 | Improved |
| use RF-DETR instead of Deformable DETR as base | EW-DETR · EWOD Pascal: VOC [1:10] -> Clipart [11:18] | FOGS: 44.82 -> 61.08 | Improved |
| EW-DETR vs best baseline ORTH | EW-DETR (RF-DETR) · EWOD Pascal: VOC [1:10] -> Clipart [11:18] | FOGS: 29.78 -> 61.08 | Improved |
| EW-DETR (Deformable DETR) vs ORTH | EW-DETR (D-DETR) · EWOD Weather: Day -> Night Sunny -> Night Rainy | FOGS: 34.38 -> 34.26 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PROB — PROB: Probabilistic Objectness for Open World Object Detection (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- OW-DETR: Open-World Detection Transformer (CVPR 2022 · similarity 0.89)
- REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling (ECCV 2026 · similarity 0.88)
- End-to-End Object Detection with Transformers (ECCV 2020 · similarity 0.87)
- Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity (ICLR 2022 · similarity 0.87)
- Open-World Objectness Modeling Unifies Novel Object Detection (CVPR 2025 · similarity 0.87)
- Exploring Orthogonality in Open World Object Detection (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
