HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Instance Segmentation On Lvis V1 0 Val

Metrics

mask AP
mask APr

Results

Performance results of various models on this benchmark

Paper Title
Co-DETR (single-scale)60.7-DETRs with Collaborative Hybrid Assignments Training
EVA55.0-EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
HTC-ealrystop-ema50.4-LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation
GLEE-Pro49.9-General Object Foundation Model for Images and Videos at Scale
ViTDet-H48.136.9Exploring Plain Vision Transformer Backbones for Object Detection
ViTDet-L46.034.3Exploring Plain Vision Transformer Backbones for Object Detection
DiverGen (Swin-L)45.545.8DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)45.443.8X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
DiffusionInst-SwinL38.6-DiffusionInst: Diffusion Model for Instance Segmentation
Eff-B7 NAS-FPN (1280, Copy-Paste pre-training))38.1-Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
DiffusionInst-SwinB36-DiffusionInst: Diffusion Model for Instance Segmentation
FRACAL-SwinS33.627.8Fractal Calibration for long-tailed object detection
SE-R101-FPN-MaskRCNN-APA30.723.6Adaptive Parametric Activation
FRACAL-SwinT30.725.7Fractal Calibration for long-tailed object detection
SE-R50-FPN-MaskRCNN-APA29.121.6Adaptive Parametric Activation
R101-FPN-MaskRCNN-GOL29.0-Long-tailed Instance Segmentation using Gumbel Optimized Loss
Cascade-R101-EQLv228.8-Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
R101-MaskRCNN-LOCE28-Exploring Classification Equilibrium in Long-Tailed Object Detection
R50-FPN-MaskRCNN-GOL27.7-Long-tailed Instance Segmentation using Gumbel Optimized Loss
R101-FPN-MaskRCNN-EQLv227.5-Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
0 of 24 row(s) selected.