Research map / Detection and segmentation / Open-set and few-shot detection
Towards Open World Object Detection
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use ORE instead of Faster R-CNN | Open World Object Detection · Open World Task 1 | WI: 0.06991 -> 0.02193 | Helped |
| Use ORE instead of Faster R-CNN | Open World Object Detection · Open World Task 2 | mAP, both known groups: 14.91 -> 38.98 | Helped |
| Use ORE instead of Faster ILOD | Incremental object detection · Pascal VOC 10+10 | mAP: 62.16 -> 64.58 | Helped |
| Add contrastive clustering to the ALU+EBUI configuration (ablation) | ORE · Task 1 unknown detection | WI: 0.04539 -> 0.02193 | Helped |
| Add energy-based unknown identification to ALU+CC (ablation) | ORE · Task 1 unknown detection | WI: 0.05614 -> 0.02193 | Helped |
| Add auto-labelling of unknowns to EBUI alone (ablation) | ORE · Task 1 unknown detection | WI: 0.05932 -> 0.04539 | Helped |
| Remove contrastive clustering while keeping ALU and EBUI (ablation) | ORE · Task 1 unknown detection | WI: 0.02193 -> 0.04539 | Hurt |
| Remove EBUI while keeping CC and ALU (ablation) | ORE · Task 1 unknown detection | WI: 0.02193 -> 0.05614 | Hurt |
| Remove ALU and EBUI, leaving the standard detector (ablation) | ORE · Task 1 unknown detection | WI: 0.02193 -> 0.06991 | Hurt |
| Increase exemplar memory from 50 to 100 instances per class (ablation) | ORE balanced finetuning · Task 2 | WI: 0.0154 -> 0.0410 | Hurt |
| Use a minimum exemplar memory of 10 instead of none (ablation) | ORE balanced finetuning · Task 2 | mAP, previously known: 8.74 -> 46.78 | Helped |
| Increase feature queue size from 5 to 20 (ablation) | ORE prototype computation · Task 1 | mAP: 56.01 -> 56.34 | No clear effect |
Closest papers by meaning
- Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection (NeurIPS 2025 · similarity 0.90)
- Open-World Objectness Modeling Unifies Novel Object Detection (CVPR 2025 · similarity 0.89)
- Detecting Open World Objects via Partial Attribute Assignment (CVPR 2025 · similarity 0.89)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · similarity 0.88)
- Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection (AAAI 2024 · similarity 0.88)
- Percept, Memory, and Imagine: World Feature Simulating for Open-Domain Unknown Object Detection (CVPR 2025 · similarity 0.88)
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.