Object Detection on Pascal VOC (Novel Split 2)
67.7nAP50ReSet
Evaluation Results
| Method | Links | |
|---|---|---|
| ReSetBackbone=ViT-L/14, Shots=52026.06 | 67.7 | |
| ReSetBackbone=ViT-L/14, Shots=32026.06 | 67.6 | |
| ReSetBackbone=ViT-L/14, Shots=102026.06 | 67.3 | |
| DE-ViTBackbone=ViT-L/14, Shots=102023.09 | 63.1 | |
| DE-ViTBackbone=ViT-L/14, Shots=102026.06 | 63.1 | |
| PiDiViTBackbone=ViT-L/14, Shots=102026.06 | 62.4 | |
| DE-ViTBackbone=ViT-L/14, Shots=52023.09 | 61.6 | |
| DE-ViTBackbone=ViT-L/14, Shots=52026.06 | 61.6 | |
| PiDiViTBackbone=ViT-L/14, Shots=32026.06 | 61.2 | |
| PiDiViTBackbone=ViT-L/14, Shots=52026.06 | 61.2 | |
| DE-ViTBackbone=ViT-S/14, Shots=102023.09 | 60.8 | |
| DE-ViTBackbone=ViT-B/14, Shots=102023.09 | 60.6 | |
| DE-ViTBackbone=ViT-B/14, Shots=52023.09 | 59.8 | |
| DE-ViTBackbone=ViT-B/14, Shots=32023.09 | 58.2 | |
| DE-ViTBackbone=ViT-L/14, Shots=32023.09 | 58.1 | |
| DE-ViTBackbone=ViT-L/14, Shots=32026.06 | 58.1 | |
| DE-ViTBackbone=ViT-S/14, Shots=52023.09 | 56.7 | |
| NIFFShots=52023.09 | 56.4 | |
| NIFFBackbone=RN101, Shots=52026.06 | 56.4 | |
| ReSetBackbone=ViT-L/14, Shots=22026.06 | 56 | |
| NIFFShots=32023.09 | 54 | |
| NIFFShots=102023.09 | 54 | |
| NIFFBackbone=RN101, Shots=32026.06 | 54 | |
| NIFFBackbone=RN101, Shots=102026.06 | 54 | |
| Meta Faster R-CNNShots=102023.09 | 51.4 | |
| Meta Faster R-CNNBackbone=RN101, Shots=102026.06 | 51.4 | |
| CrossTransformerShots=102023.09 | 51.2 | |
| CrossTransformerBackbone=PVTv2, Shots=102026.06 | 51.2 | |
| HeteroGraphShots=102023.09 | 51.1 | |
| HeteroGraphBackbone=RN101, Shots=102026.06 | 51.1 | |
| ReSetBackbone=ViT-L/14, Shots=12026.06 | 50.8 | |
| LVCShots=32023.09 | 50.7 | |
| LVCBackbone=ViT-S/8, Shots=32026.06 | 50.7 | |
| LVCShots=102023.09 | 50.6 | |
| LVCBackbone=ViT-S/8, Shots=102026.06 | 50.6 | |
| LVCShots=52023.09 | 49.8 | |
| LVCBackbone=ViT-S/8, Shots=52026.06 | 49.8 | |
| DE-ViTBackbone=ViT-S/14, Shots=32023.09 | 49.7 | |
| CrossTransformerShots=52023.09 | 49.2 | |
| CrossTransformerBackbone=PVTv2, Shots=52026.06 | 49.2 | |
| DiGeoShots=102023.09 | 49.1 | |
| DiGeoBackbone=RN101, Shots=102026.06 | 49.1 | |
| HeteroGraphShots=52023.09 | 48.9 | |
| HeteroGraphBackbone=RN101, Shots=52026.06 | 48.9 | |
| Meta Faster R-CNNShots=52023.09 | 47.8 | |
| Meta Faster R-CNNBackbone=RN101, Shots=52026.06 | 47.8 | |
| Multi-Relation DetShots=102023.09 | 47.6 | |
| Multi-Relation DetBackbone=RN50, Shots=102026.06 | 47.6 | |
| DE-ViTBackbone=ViT-B/14, Shots=22023.09 | 47.3 | |
| HeteroGraphShots=32023.09 | 46.6 | |
| HeteroGraphBackbone=RN101, Shots=32026.06 | 46.6 | |
| Meta Faster R-CNNShots=32023.09 | 46.1 | |
| Meta Faster R-CNNBackbone=RN101, Shots=32026.06 | 46.1 | |
| DE-ViTBackbone=ViT-B/14, Shots=12023.09 | 45.3 | |
| PiDiViTBackbone=ViT-L/14, Shots=22026.06 | 44.7 | |
| CrossTransformerShots=32023.09 | 43.7 | |
| CrossTransformerBackbone=PVTv2, Shots=32026.06 | 43.7 | |
| PiDiViTBackbone=ViT-L/14, Shots=12026.06 | 43.5 | |
| Multi-Relation DetShots=52023.09 | 43.1 | |
| DE-ViTBackbone=ViT-S/14, Shots=12023.09 | 43.1 | |
| Multi-Relation DetBackbone=RN50, Shots=52026.06 | 43.1 | |
| DE-ViTBackbone=ViT-L/14, Shots=12023.09 | 43 | |
| DE-ViTBackbone=ViT-L/14, Shots=12026.06 | 43 | |
| NIFFShots=22023.09 | 42.9 | |
| NIFFBackbone=RN101, Shots=22026.06 | 42.9 | |
| DiGeoShots=52023.09 | 42.1 | |
| DiGeoBackbone=RN101, Shots=52026.06 | 42.1 | |
| DiGeoShots=32023.09 | 41.9 | |
| DiGeoBackbone=RN101, Shots=32026.06 | 41.9 | |
| Multi-Relation DetShots=32023.09 | 40.7 | |
| Multi-Relation DetBackbone=RN50, Shots=32026.06 | 40.7 | |
| Retentive RCNNShots=102023.09 | 40.3 | |
| Retentive RCNNBackbone=RN101, Shots=102026.06 | 40.3 | |
| DE-ViTBackbone=ViT-L/14, Shots=22023.09 | 39.3 | |
| DE-ViTBackbone=ViT-L/14, Shots=22026.06 | 39.3 | |
| TFAShots=102023.09 | 39.1 | |
| TFABackbone=RN101, Shots=102026.06 | 39.1 | |
| NIFFShots=12023.09 | 38.4 | |
| NIFFBackbone=RN101, Shots=12026.06 | 38.4 | |
| HeteroGraphShots=22023.09 | 37.8 | |
| HeteroGraphBackbone=RN101, Shots=22026.06 | 37.8 | |
| Retentive RCNNShots=52023.09 | 37 | |
| Retentive RCNNBackbone=RN101, Shots=52026.06 | 37 | |
| Meta Faster R-CNNShots=22023.09 | 35.5 | |
| Meta Faster R-CNNBackbone=RN101, Shots=22026.06 | 35.5 | |
| Retentive RCNNShots=32023.09 | 35.2 | |
| Retentive RCNNBackbone=RN101, Shots=32026.06 | 35.2 | |
| TFAShots=52023.09 | 35.1 | |
| TFABackbone=RN101, Shots=52026.06 | 35.1 | |
| CrossTransformerShots=22023.09 | 34.5 | |
| CrossTransformerBackbone=PVTv2, Shots=22026.06 | 34.5 | |
| TFAShots=32023.09 | 34.1 | |
| DE-ViTBackbone=ViT-S/14, Shots=22023.09 | 34.1 | |
| TFABackbone=RN101, Shots=32026.06 | 34.1 | |
| LVCShots=12023.09 | 32.8 | |
| LVCBackbone=ViT-S/8, Shots=12026.06 | 32.8 | |
| Multi-Relation DetShots=22023.09 | 30.6 | |
| Multi-Relation DetBackbone=RN50, Shots=22026.06 | 30.6 | |
| FsDetViewShots=102023.09 | 29.2 | |
| LVCShots=22023.09 | 29.2 |