Object Detection on Pascal VOC (Novel Split 3)
74.6AP50ReSet
Evaluation Results
| Method | Links | |
|---|---|---|
| ReSetBackbone=ViT-L/14, Shots=102026.06 | 74.6 | |
| ReSetBackbone=ViT-L/14, Shots=52026.06 | 72.8 | |
| ReSetBackbone=ViT-L/14, Shots=22026.06 | 72 | |
| ReSetBackbone=ViT-L/14, Shots=32026.06 | 68.9 | |
| DE-ViTBackbone=ViT-B/14, Shots=102023.09 | 67.8 | |
| PiDiViTBackbone=ViT-L/14, Shots=102026.06 | 67.6 | |
| DE-ViTBackbone=ViT-L/14, Shots=102023.09 | 67.3 | |
| DE-ViTBackbone=ViT-L/14, Shots=102026.06 | 67.3 | |
| ReSetBackbone=ViT-L/14, Shots=12026.06 | 65.5 | |
| DE-ViTBackbone=ViT-B/14, Shots=52023.09 | 64.6 | |
| DE-ViTBackbone=ViT-S/14, Shots=102023.09 | 64.5 | |
| DE-ViTBackbone=ViT-L/14, Shots=52023.09 | 64.2 | |
| DE-ViTBackbone=ViT-L/14, Shots=52026.06 | 64.2 | |
| PiDiViTBackbone=ViT-L/14, Shots=22026.06 | 64.2 | |
| NIFFShots=52023.09 | 64.1 | |
| NIFFBackbone=RN101, Shots=52026.06 | 64.1 | |
| PiDiViTBackbone=ViT-L/14, Shots=52026.06 | 64.1 | |
| DE-ViTBackbone=ViT-L/14, Shots=22023.09 | 64 | |
| DE-ViTBackbone=ViT-L/14, Shots=22026.06 | 64 | |
| NIFFShots=102023.09 | 63.9 | |
| NIFFBackbone=RN101, Shots=102026.06 | 63.9 | |
| DE-ViTBackbone=ViT-B/14, Shots=32023.09 | 62.7 | |
| DE-ViTBackbone=ViT-B/14, Shots=22023.09 | 62.3 | |
| NIFFShots=22023.09 | 62.1 | |
| DE-ViTBackbone=ViT-B/14, Shots=12023.09 | 62.1 | |
| NIFFBackbone=RN101, Shots=22026.06 | 62.1 | |
| DE-ViTBackbone=ViT-S/14, Shots=52023.09 | 61.4 | |
| PiDiViTBackbone=ViT-L/14, Shots=32026.06 | 61.4 | |
| DE-ViTBackbone=ViT-L/14, Shots=32023.09 | 61.3 | |
| DE-ViTBackbone=ViT-L/14, Shots=32026.06 | 61.3 | |
| NIFFShots=32023.09 | 61.2 | |
| NIFFBackbone=RN101, Shots=32026.06 | 61.2 | |
| DE-ViTBackbone=ViT-S/14, Shots=32023.09 | 60.7 | |
| Meta Faster R-CNNShots=52023.09 | 59.9 | |
| Meta Faster R-CNNBackbone=RN101, Shots=52026.06 | 59.9 | |
| LVCShots=52023.09 | 59.6 | |
| LVCShots=102023.09 | 59.6 | |
| LVCBackbone=ViT-S/8, Shots=52026.06 | 59.6 | |
| LVCBackbone=ViT-S/8, Shots=102026.06 | 59.6 | |
| CrossTransformerShots=102023.09 | 58.7 | |
| CrossTransformerBackbone=PVTv2, Shots=102026.06 | 58.7 | |
| Meta Faster R-CNNShots=102023.09 | 58.6 | |
| DE-ViTBackbone=ViT-S/14, Shots=22023.09 | 58.6 | |
| Meta Faster R-CNNBackbone=RN101, Shots=102026.06 | 58.6 | |
| PiDiViTBackbone=ViT-L/14, Shots=12026.06 | 58.4 | |
| DE-ViTBackbone=ViT-L/14, Shots=12023.09 | 58.2 | |
| DE-ViTBackbone=ViT-L/14, Shots=12026.06 | 58.2 | |
| CrossTransformerShots=52023.09 | 57 | |
| CrossTransformerBackbone=PVTv2, Shots=52026.06 | 57 | |
| NIFFShots=12023.09 | 56.4 | |
| NIFFBackbone=RN101, Shots=12026.06 | 56.4 | |
| LVCShots=32023.09 | 55 | |
| LVCBackbone=ViT-S/8, Shots=32026.06 | 55 | |
| HeteroGraphShots=52023.09 | 54.8 | |
| HeteroGraphBackbone=RN101, Shots=52026.06 | 54.8 | |
| CrossTransformerShots=22023.09 | 54.7 | |
| DiGeoShots=102023.09 | 54.7 | |
| CrossTransformerBackbone=PVTv2, Shots=22026.06 | 54.7 | |
| DiGeoBackbone=RN101, Shots=102026.06 | 54.7 | |
| HeteroGraphShots=102023.09 | 53.5 | |
| HeteroGraphBackbone=RN101, Shots=102026.06 | 53.5 | |
| Meta Faster R-CNNShots=32023.09 | 53.4 | |
| Meta Faster R-CNNBackbone=RN101, Shots=32026.06 | 53.4 | |
| LVCShots=22023.09 | 52.7 | |
| DiGeoShots=52023.09 | 52.7 | |
| LVCBackbone=ViT-S/8, Shots=22026.06 | 52.7 | |
| DiGeoBackbone=RN101, Shots=52026.06 | 52.7 | |
| DE-ViTBackbone=ViT-S/14, Shots=12023.09 | 52.5 | |
| CrossTransformerShots=32023.09 | 52.3 | |
| CrossTransformerBackbone=PVTv2, Shots=32026.06 | 52.3 | |
| Multi-Relation DetShots=52023.09 | 51.3 | |
| Multi-Relation DetBackbone=RN50, Shots=52026.06 | 51.3 | |
| Retentive RCNNShots=102023.09 | 50.1 | |
| Retentive RCNNBackbone=RN101, Shots=102026.06 | 50.1 | |
| TFAShots=102023.09 | 49.8 | |
| Multi-Relation DetShots=102023.09 | 49.8 | |
| TFABackbone=RN101, Shots=102026.06 | 49.8 | |
| Multi-Relation DetBackbone=RN50, Shots=102026.06 | 49.8 | |
| Retentive RCNNShots=52023.09 | 49.7 | |
| Retentive RCNNBackbone=RN101, Shots=52026.06 | 49.7 | |
| TFAShots=52023.09 | 49.5 | |
| TFABackbone=RN101, Shots=52026.06 | 49.5 | |
| LVCShots=12023.09 | 48.4 | |
| LVCBackbone=ViT-S/8, Shots=12026.06 | 48.4 | |
| HeteroGraphShots=32023.09 | 47.8 | |
| HeteroGraphBackbone=RN101, Shots=32026.06 | 47.8 | |
| DiGeoShots=32023.09 | 46.9 | |
| DiGeoBackbone=RN101, Shots=32026.06 | 46.9 | |
| Meta Faster R-CNNShots=22023.09 | 46.4 | |
| Meta Faster R-CNNBackbone=RN101, Shots=22026.06 | 46.4 | |
| Multi-Relation DetShots=32023.09 | 43.7 | |
| Multi-Relation DetBackbone=RN50, Shots=32026.06 | 43.7 | |
| Retentive RCNNShots=32023.09 | 43 | |
| Retentive RCNNBackbone=RN101, Shots=32026.06 | 43 | |
| HeteroGraphShots=22023.09 | 42.9 | |
| HeteroGraphBackbone=RN101, Shots=22026.06 | 42.9 | |
| TFAShots=32023.09 | 42.8 | |
| TFABackbone=RN101, Shots=32026.06 | 42.8 | |
| Meta Faster R-CNNShots=12023.09 | 40.6 | |
| Meta Faster R-CNNBackbone=RN101, Shots=12026.06 | 40.6 |