Scene Recognition on SUN 397 (val)
78.93AccuracySOSF+CFA+GAF
Evaluation Results
| Method | Links | |
|---|---|---|
| SOSF+CFA+GAFAdditional data=Object177, Input Resolution=608x6082019.07 | 78.93 | |
| FOSNetFusion Level=feature level, Fusion strategy=mixed CCM-CCG, Input Resolution=224x2242019.07 | 77.28 | |
| FOSNetFusion Level=feature level, Fusion strategy=CCG, Input Resolution=224x2242019.07 | 76.62 | |
| SE-ResNeXt-101 + SCLBackbone=SE-ResNeXt-101, Feature Mode=Single scene feature2019.07 | 76.27 | |
| FOSNetFusion Level=feature level, Fusion strategy=Concatenate, Input Resolution=224x2242019.07 | 75.57 | |
| FOSNetFusion Level=feature level, Fusion strategy=Sum, Input Resolution=224x2242019.07 | 75.32 | |
| Adi-Red2019.07 | 73.59 | |
| SDO2019.07 | 73.41 | |
| PatchNet2019.07 | 73 | |
| CNN-SMN2019.07 | 72.6 | |
| Multi-Resolution CNNs2019.07 | 72 | |
| Sparse Representation2019.07 | 71.08 | |
| Hybrid CNN2019.07 | 70.69 | |
| Three2019.07 | 70.17 | |
| Places365-VGG-SVMBackbone=VGG, Pre-training=Places3652019.07 | 63.24 | |
| MetaObject-CNN2019.07 | 58.11 | |
| DAG-CNN2019.07 | 56.2 | |
| Gaze Shifting-CNN+SVM2019.07 | 56.2 | |
| VS-CNN2019.07 | 43.14 |