HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Semantic Segmentation On Imagenet S

Metrics

mIoU (test)
mIoU (val)

Results

Performance results of various models on this benchmark

Paper Title
TEC (ViT-B/16, 224x224, SSL+FT, mmseg)62.563.2Towards Sustainable Self-supervised Learning
SERE (ViT-B/16, 100ep, 224x224, SSL+FT)63.363.0SERE: Exploring Feature Self-relation for Self-supervised Transformer
TEC (ViT-B/16, 224x224, SSL+FT)-62.0Towards Sustainable Self-supervised Learning
MAE (ViT-B/16, 224x224, SSL+FT, mmseg)61.261.6Masked Autoencoders Are Scalable Vision Learners
MAE (ViT-B/16, 224x224, SSL+FT)60.261.0Masked Autoencoders Are Scalable Vision Learners
SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg)59.059.4SERE: Exploring Feature Self-relation for Self-supervised Transformer
SERE (ViT-S/16, 100ep, 224x224, SSL+FT)57.858.9SERE: Exploring Feature Self-relation for Self-supervised Transformer
RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP)51.151.3RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP)50.550.8RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP)50.550.7RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
ConvNext-Tiny (P4, 224x224, SUP)48.848.7A ConvNet for the 2020s
SERE (ViT-B/16, 100ep, 224x224, SSL)48.248.6SERE: Exploring Feature Self-relation for Self-supervised Transformer
TEC (ViT-B/16, 224x224, SSL, mmseg)46.046.1Towards Sustainable Self-supervised Learning
TEC (ViT-B/16, 224x224, SSL)-42.9Towards Sustainable Self-supervised Learning
SERE (ViT-S/16, 100ep, 224x224, SSL)40.241.0SERE: Exploring Feature Self-relation for Self-supervised Transformer
SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg)40.541.0SERE: Exploring Feature Self-relation for Self-supervised Transformer
MAE (ViT-B/16, 224x224, SSL, mmseg)40.340.0Masked Autoencoders Are Scalable Vision Learners
MAE (ViT-B/16, 224x224, SSL)37.038.3Masked Autoencoders Are Scalable Vision Learners
PASS (ResNet-50 D16, 224x224, LUSS)20.821.6Large-scale Unsupervised Semantic Segmentation
PASS (ResNet-50 D32, 224x224, LUSS)20.321.0Large-scale Unsupervised Semantic Segmentation
0 of 20 row(s) selected.