| Towards Sustainable Self-supervised Learning | ✓ Link | 63.2 | 62.5 | TEC (ViT-B/16, 224x224, SSL+FT, mmseg) | 2022-10-20 |
| SERE: Exploring Feature Self-relation for Self-supervised Transformer | ✓ Link | 63.0 | 63.3 | SERE (ViT-B/16, 100ep, 224x224, SSL+FT) | 2022-06-10 |
| Towards Sustainable Self-supervised Learning | ✓ Link | 62.0 | | TEC (ViT-B/16, 224x224, SSL+FT) | 2022-10-20 |
| Masked Autoencoders Are Scalable Vision Learners | ✓ Link | 61.6 | 61.2 | MAE (ViT-B/16, 224x224, SSL+FT, mmseg) | 2021-11-11 |
| Masked Autoencoders Are Scalable Vision Learners | ✓ Link | 61.0 | 60.2 | MAE (ViT-B/16, 224x224, SSL+FT) | 2021-11-11 |
| SERE: Exploring Feature Self-relation for Self-supervised Transformer | ✓ Link | 59.4 | 59.0 | SERE (ViT-S/16, 100ep, 224x224, SSL+FT, mmseg) | 2022-06-10 |
| SERE: Exploring Feature Self-relation for Self-supervised Transformer | ✓ Link | 58.9 | 57.8 | SERE (ViT-S/16, 100ep, 224x224, SSL+FT) | 2022-06-10 |
| RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks | ✓ Link | 51.3 | 51.1 | RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP) | 2022-06-14 |
| RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks | ✓ Link | 50.8 | 50.5 | RF-ConvNext-Tiny (rfmultiple, P4, 224x224, SUP) | 2022-06-14 |
| RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks | ✓ Link | 50.7 | 50.5 | RF-ConvNext-Tiny (rfsingle, P4, 224x224, SUP) | 2022-06-14 |
| A ConvNet for the 2020s | ✓ Link | 48.7 | 48.8 | ConvNext-Tiny (P4, 224x224, SUP) | 2022-01-10 |
| SERE: Exploring Feature Self-relation for Self-supervised Transformer | ✓ Link | 48.6 | 48.2 | SERE (ViT-B/16, 100ep, 224x224, SSL) | 2022-06-10 |
| Towards Sustainable Self-supervised Learning | ✓ Link | 46.1 | 46.0 | TEC (ViT-B/16, 224x224, SSL, mmseg) | 2022-10-20 |
| Towards Sustainable Self-supervised Learning | ✓ Link | 42.9 | | TEC (ViT-B/16, 224x224, SSL) | 2022-10-20 |
| SERE: Exploring Feature Self-relation for Self-supervised Transformer | ✓ Link | 41.0 | 40.5 | SERE (ViT-S/16, 100ep, 224x224, SSL, mmseg) | 2022-06-10 |
| SERE: Exploring Feature Self-relation for Self-supervised Transformer | ✓ Link | 41.0 | 40.2 | SERE (ViT-S/16, 100ep, 224x224, SSL) | 2022-06-10 |
| Masked Autoencoders Are Scalable Vision Learners | ✓ Link | 40.0 | 40.3 | MAE (ViT-B/16, 224x224, SSL, mmseg) | 2021-11-11 |
| Masked Autoencoders Are Scalable Vision Learners | ✓ Link | 38.3 | 37.0 | MAE (ViT-B/16, 224x224, SSL) | 2021-11-11 |
| Large-scale Unsupervised Semantic Segmentation | ✓ Link | 21.6 | 20.8 | PASS (ResNet-50 D16, 224x224, LUSS) | 2021-06-06 |
| Large-scale Unsupervised Semantic Segmentation | ✓ Link | 21.0 | 20.3 | PASS (ResNet-50 D32, 224x224, LUSS) | 2021-06-06 |