List your company
ResearchFormerly WizWand

Described Object Detection on D3 (Full)

32.5mAPAPE-Ti + NEGTOME
3.06810.70918.3525.991Oct 15, 2025
Updated 7mo ago

Evaluation results

MethodLinks
APE-Ti + NEGTOMEBackbone=ViT-Ti, Text Encoder=CLIP, Detection Head=DETA2025.1032.5
APE-TiBackbone=ViT-Ti, Text Encoder=CLIP, Detection Head=DETA2025.1029.1
G-DINO-B + NEGTOMEBackbone=Swin-B, Text Encoder=BERT, Detection Head=DINO2025.1027.3
FIBER-B + W2SBackbone=Swin-B, Text Encoder=RoBERTa-B, Detection Head=DyHead2025.1026.5
GLIP-T + W2SBackbone=Swin-T, Text Encoder=BERT, Detection Head=DyHead2025.1026
FIBER-B + GENBackbone=Swin-B, Text Encoder=RoBERTa-B, Detection Head=DyHead2025.1026
FIBER-BBackbone=Swin-B, Text Encoder=RoBERTa-B, Detection Head=DyHead2025.1022.7
Qwen-2.5-VL-3B + NEGTOMEBackbone=ViT-H, Text Encoder=Qwen-2.5, Detection Head=-2025.1022.2
OFA-DODBackbone=ResNet-101+ViT, Text Encoder=BART, Detection Head=Seq2Seq2025.1021.6
GLIP-T + GENBackbone=Swin-T, Text Encoder=BERT, Detection Head=DyHead2025.1021.4
G-DINO-BBackbone=Swin-B, Text Encoder=BERT, Detection Head=DINO2025.1020.7
GLIP-TBackbone=Swin-T, Text Encoder=BERT, Detection Head=DyHead2025.1019.1
Qwen-2.5-VL-3BBackbone=ViT-H, Text Encoder=Qwen-2.5, Detection Head=-2025.1018.6
SPHINX-7BBackbone=CLIP,DINO-v2, Q-Former, Text Encoder=LLaMA-2, Detection Head=-2025.1010.6
OWL-ViT-LBackbone=ViT-L, Text Encoder=CLIP, Detection Head=OWL-ViT2025.109.6
OFA-LBackbone=ResNet-101+ViT, Text Encoder=BART, Detection Head=Seq2Seq2025.104.2