List your company

Open-vocabulary Object Detection on COCO

42.1AP (Novel)Grounding DINO-T
28.89232.32135.7539.179Apr 3, 2026

Evaluation results

MethodLinks
Grounding DINO-TBackbone=Swin-T, Text Enc.=BERT-Base, Latency (ms)=∼280, FPS=3.52026.0442.1
DeCo-DETRBackbone=ResNet-50, Latency (ms)=135, FPS=7.42026.0441.3
CAKEBackbone=ResNet-50, Latency (ms)=145, FPS=6.92026.0438.2
VL-PLMBackbone=ResNet-50, Text Enc.=RoBERTa, Latency (ms)=∼210, FPS=4.72026.0432.3
DetProBackbone=ResNet-50, Latency (ms)=250, FPS=4.02026.0429.4