HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Object Detection On Lvis V1 0 Val

Metrics

box AP

Results

Performance results of various models on this benchmark

Model Name
box AP
Paper TitleRepository
R101-MaskRCNN-LOCE29Exploring Classification Equilibrium in Long-Tailed Object Detection-
DiverGen (Swin-L)51.2DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)50.9X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Co-DETR (single-scale)68.0DETRs with Collaborative Hybrid Assignments Training
GLEE-Pro55.7General Object Foundation Model for Images and Videos at Scale
ViTDet-L51.2Exploring Plain Vision Transformer Backbones for Object Detection
Grounding DINO 1.5 Pro63.5Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
EVA62.2EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
R50-MaskRCNN-LOCE27.4Exploring Classification Equilibrium in Long-Tailed Object Detection-
InternImage-H63.2InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))41.6Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
RichSem (Focal-H + ImageNet as weakly-supervised extra data)61.2Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
ViTDet-H53.4Exploring Plain Vision Transformer Backbones for Object Detection
0 of 13 row(s) selected.