| VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection | | 60.2 | VL-SAM-v3 + SAM3 | 2026-05-05 |
| CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection | | 58.2 | CP-DETR-Pro(without LVIS data) | 2024-12-13 |
| Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | ✓ Link | 57.7 | Grounding DINO 1.6 Pro (without LVIS data) | 2024-05-16 |
| Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection | ✓ Link | 55.7 | Grounding DINO 1.5 Pro (without LVIS data) | 2024-05-16 |
| WeDetect: Fast Open-Vocabulary Object Detection as Retrieval | ✓ Link | 55.0 | WeDetect-Large | 2025-12-13 |
| VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection | | 53.4 | VL-SAM-v3 (Swin-L) | 2026-05-05 |
| Scaling Open-Vocabulary Object Detection | ✓ Link | 51.3 | OWLv2 (OWL-ST+FT) | 2023-06-16 |
| VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection | | 47.7 | VL-SAM-v3 (Swin-T) | 2026-05-05 |
| WeDetect: Fast Open-Vocabulary Object Detection as Retrieval | ✓ Link | 47.3 | WeDetect-Base | 2025-12-13 |
| Multi-modal Queried Object Detection in the Wild | ✓ Link | 43.4 | MQ-GLIP-L | 2023-05-30 |
| An Open and Comprehensive Pipeline for Unified Object Grounding and Detection | ✓ Link | 41.4 | MM-Grounding-DINO-T (zero-shot) | 2024-01-04 |
| OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion | ✓ Link | 40.1 | OV-DINO-T (without LVIS data, swin tiny) | 2024-07-10 |
| WeDetect: Fast Open-Vocabulary Object Detection as Retrieval | ✓ Link | 37.4 | WeDetect-Tiny | 2025-12-13 |
| Grounded Language-Image Pre-training | ✓ Link | 37.3 | GLIP-L | 2021-12-07 |
| ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding | | 37.2 | ExpAlign (ConvNeXt-T, OG pre-train) | 2026-01-30 |
| YOLO-World: Real-Time Open-Vocabulary Object Detection | ✓ Link | 35.4 | YOLO-World-L | 2024-01-30 |
| Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head | ✓ Link | 34.7 | OmDet-Turbo-Base (zero-shot) | 2024-03-11 |
| Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection | ✓ Link | 33.9 | GroundingDINO-L | 2023-03-09 |
| Multi-modal Queried Object Detection in the Wild | ✓ Link | 30.4 | MQ-GLIP-T | 2023-05-30 |
| Multi-modal Queried Object Detection in the Wild | ✓ Link | 30.2 | MQ-GroundingDINO-T | 2023-05-30 |