Object Detection On Lvis V1 0 Val

Metrics

box AP

Results

Performance results of various models on this benchmark

		Paper Title
Co-DETR (single-scale)	68.0	DETRs with Collaborative Hybrid Assignments Training
Grounding DINO 1.5 Pro	63.5	Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
InternImage-H	63.2	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
EVA	62.2	EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
RichSem (Focal-H + ImageNet as weakly-supervised extra data)	61.2	Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
GLEE-Pro	55.7	General Object Foundation Model for Images and Videos at Scale
ViTDet-H	53.4	Exploring Plain Vision Transformer Backbones for Object Detection
DiverGen (Swin-L)	51.2	DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
ViTDet-L	51.2	Exploring Plain Vision Transformer Backbones for Object Detection
CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)	50.9	X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))	41.6	Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
R101-MaskRCNN-LOCE	29	Exploring Classification Equilibrium in Long-Tailed Object Detection
R50-MaskRCNN-LOCE	27.4	Exploring Classification Equilibrium in Long-Tailed Object Detection

0 of 13 row(s) selected.