Research map / Detection and segmentation / Open-set and few-shot detection
Benefit From Seen: Enhancing Open-Vocabulary Object Detection by Bridging Visual and Textual Co-Occurrence Knowledge
Yanqi Li, Jianwei Niu, Tao Ren
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 CODet co-occurrence knowledge | ViLD · OV-COCO | AP novel: 27.6 -> 29.2 | Improved |
| add CODet co-occurrence knowledge | BARON · OV-COCO | AP novel: 33.1 -> 35.2 | Improved |
| add CODet co-occurrence knowledge | Detic · OV-COCO | AP novel: 27.8 -> 29.8 | Improved |
| add CODet co-occurrence knowledge | VLDet · OV-COCO | AP novel: 32.0 -> 33.9 | Improved |
| add CODet co-occurrence knowledge | ViLD · OV-COCO | AP known: 59.5 -> 61.3 | Improved |
| add CODet co-occurrence knowledge | Detic (Swin-B) · OV-LVIS | mask AP novel: 23.9 -> 25.6 | Improved |
| add CODet co-occurrence knowledge | VLDet (Swin-B) · OV-LVIS | mask AP novel: 26.3 -> 27.9 | Improved |
| add CODet co-occurrence knowledge | RegionCLIP (RN50) · OV-LVIS | mask AP common: 27.4 -> 29.4 | Improved |
| add CODet co-occurrence knowledge | VLDet · PASCAL VOC zero-shot | mAP novel: 61.7 -> 64.3 | Improved |
| add CODet co-occurrence knowledge | VLDet · LVIS zero-shot | mAP novel: 10 -> 12.3 | Improved |
| use spatial proximity query Q1 instead of functional query Q2 alone (ablation) | VLDet-CODet · OV-COCO | mAP novel: 33.0 vs 32.5 | Improved |
| add functional query Q2 to Q1 (ablation) | VLDet-CODet · OV-COCO | mAP novel: 33.0 -> 33.4 | Improved |
Closest papers by meaning
- Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection (ICLR 2025 · similarity 0.91)
- Simple Image-Level Classification Improves Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.91)
- LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors (ICLR 2024 · similarity 0.91)
- CAKE: Category Aware Knowledge Extraction for Open-Vocabulary Object Detection (AAAI 2025 · similarity 0.90)
- The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding (CVPR 2024 · similarity 0.90)
- How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection (AAAI 2024 · similarity 0.90)
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.
