SOTAVerified

Open Vocabulary Object Detection

Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded (open) vocabulary at inference.

Papers

Showing 110 of 145 papers

TitleStatusHype
ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction0
Gen-n-Val: Agentic Image Data Generation and Validation0
From Data to Modeling: Fully Open-vocabulary Scene Graph Generation0
FG-CLIP: Fine-Grained Visual and Textual AlignmentCode4
VLM-R1: A Stable and Generalizable R1-style Large Vision-Language ModelCode9
Superpowering Open-Vocabulary Object Detectors for X-ray VisionCode1
An Iterative Feedback Mechanism for Improving Natural Language Class Descriptions in Open-Vocabulary Object Detection0
Fine-Grained Open-Vocabulary Object Detection with Fined-Grained Prompts: Task, Dataset and Benchmark0
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data GenerationCode0
Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object DetectionCode0
Show:102550
← PrevPage 1 of 15Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Cooperative Foundational ModelsAP 0.550.3Unverified
2DE-ViTAP 0.550Unverified
3Yolov8-nanoAP 0.547.2Unverified
4DITOAP 0.546.1Unverified
5OV-DQUO(RN50x4)AP 0.545.6Unverified
6LP-OVOD (OWL-ViT Proposals)AP 0.544.9Unverified
7CLIPSelfAP 0.544.3Unverified
8CORA+AP 0.543.1Unverified
9BARONAP 0.542.7Unverified
10SIA-OVD (RN50x4)AP 0.541.9Unverified