| The Detector Teaches Itself: Lightweight Self-Supervised Adaptation for Open-Vocabulary Object Detection | | 70.1 | DAT | 2026-05-05 |
| Enhancing Novel Object Detection via Cooperative Foundational Models | ✓ Link | 50.3 | Cooperative Foundational Models | 2023-11-19 |
| Detect Everything with Few Examples | ✓ Link | 50 | DE-ViT | 2023-09-22 |
| YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes | | 47.2 | Yolov8-nano | 2023-10-31 |
| Region-centric Image-Language Pretraining for Open-Vocabulary Detection | ✓ Link | 46.1 | DITO | 2023-09-29 |
| OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision | ✓ Link | 45.6 | OV-DQUO(RN50x4) | 2024-05-28 |
| LP-OVOD: Open-Vocabulary Object Detection by Linear Probing | ✓ Link | 44.9 | LP-OVOD (OWL-ViT Proposals) | 2023-10-26 |
| CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction | ✓ Link | 44.3 | CLIPSelf | 2023-10-02 |
| CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching | ✓ Link | 43.1 | CORA+ | 2023-03-23 |
| Aligning Bag of Regions for Open-Vocabulary Object Detection | ✓ Link | 42.7 | BARON | 2023-02-27 |
| SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection | ✓ Link | 41.9 | SIA-OVD (RN50x4) | 2024-10-08 |
| CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching | ✓ Link | 41.7 | CORA | 2023-03-23 |
| Retrieval-Augmented Open-Vocabulary Object Detection | ✓ Link | 41.3 | RALF | 2024-04-08 |
| LP-OVOD: Open-Vocabulary Object Detection by Linear Probing | ✓ Link | 40.5 | LP-OVOD | 2023-10-26 |
| RegionCLIP: Region-based Language-Image Pretraining | ✓ Link | 39.3 | Region-CLIP (RN50x4-C4) | 2021-12-16 |
| OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision | ✓ Link | 39.2 | OV-DQUO(R50) | 2024-05-28 |
| Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection | ✓ Link | 36.9 | Object-Centric-OVD | 2022-07-07 |
| CLIM: Contrastive Language-Image Mosaic for Region Representation | ✓ Link | 36.9 | CLIM (RN50) | 2023-12-18 |
| Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection | ✓ Link | 35.6 | OADP (G-OVD) | 2023-03-10 |
| SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection | ✓ Link | 35.5 | SIA-OVD (RN50) | 2024-10-08 |
| Exploiting Unlabeled Data with Vision and Language Models for Object Detection | ✓ Link | 34.4 | VL-PLM (RN50) | 2022-07-18 |
| Contrastive Feature Masking Open-Vocabulary Vision Transformer | | 34.1 | CFM-ViT | 2023-09-02 |
| Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization | ✓ Link | 32.6 | MEDet (RN50) | 2022-06-22 |
| RegionCLIP: Region-based Language-Image Pretraining | ✓ Link | 31.4 | Region-CLIP (RN50-C4) | 2021-12-16 |
| Open-vocabulary Attribute Detection | ✓ Link | 30.0 | OVAD-Baseline | 2022-11-23 |
| Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection | ✓ Link | 30.0 | OADP | 2023-03-10 |
| Open-Vocabulary DETR with Conditional Matching | ✓ Link | 29.4 | OV-DERT | 2022-03-22 |
| Localized Vision-Language Matching for Open-vocabulary Object Detection | ✓ Link | 28.6 | LocOv (RN50-C4) | 2022-05-12 |
| Detecting Twenty-thousand Classes using Image-level Supervision | ✓ Link | 27.8 | Detic | 2022-01-07 |
| Open-vocabulary Object Detection via Vision and Language Knowledge Distillation | ✓ Link | 27.6 | ViLD | 2021-04-28 |
| Open-Vocabulary Object Detection Using Captions | ✓ Link | 22.8 | OVR-CNN | 2020-11-20 |
| Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation | ✓ Link | 20.3 | HierKD | 2022-03-20 |
| YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection | ✓ Link | 0.5 | Yolov8 | 2024-02-14 |