Sequential Image Classification On Sequential 1
Métriques
Unpermuted Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Unpermuted Accuracy |
|---|---|
| efficiently-modeling-long-sequences-with-1 | 91.80% |
| smpconv-self-moving-point-representations-for | 84.86% |
| learning-longer-term-dependencies-in-rnns | 62.2% |
| recursive-construction-of-stable-assemblies | 65.72 |
| sequence-modeling-with-multiresolution | 93.15% |
| combining-recurrent-convolutional-and | 84.65% |
| ckconv-continuous-kernel-convolution-for | 63.74% |
| resurrecting-recurrent-neural-networks-for | 89.0 |
| lipschitz-recurrent-neural-networks | 64.2 |
| flexconv-continuous-kernel-convolutions-with-1 | 80.82% |
| trellis-networks-for-sequence-modeling | 73.42% |
| improving-the-gating-mechanism-of-recurrent-1 | 74.4% |
| ckconv-continuous-kernel-convolution-for | 62.25% |