Sequential Image Classification On Sequential
Métriques
Permuted Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Permuted Accuracy |
|---|---|
| unicornn-a-recurrent-model-for-learning-very | 98.4 |
| ckconv-continuous-kernel-convolution-for | 98.54% |
| dilated-recurrent-neural-networks | 94.6% |
| flexconv-continuous-kernel-convolutions-with-1 | - |
| combining-recurrent-convolutional-and | 98.76% |
| long-expressive-memory-for-sequence-modeling-1 | 96.6% |
| gating-revisited-deep-multi-layer-rnns-that-1 | - |
| recurrent-highway-networks-with-grouped | 96.8% |
| ckconv-continuous-kernel-convolution-for | 98% |
| recurrent-batch-normalization | 95.4% |
| recursive-construction-of-stable-assemblies | 96.94 |
| an-empirical-evaluation-of-generic | 97.2% |
| egru-event-based-gru-for-activity-sparse | 95.1% |
| flexconv-continuous-kernel-convolutions-with-1 | 98.72% |
| hippo-recurrent-memory-with-optimal | 98.3% |
| deep-independently-recurrent-neural-network | 97.2% |
| coupled-oscillatory-recurrent-neural-network | 97.34% |
| adaptive-saturated-rnn-remember-more-with-1 | 96.96% |
| legendre-memory-units-continuous-time | 97.2% |
| learning-long-term-dependencies-in | 97.83% |
| full-capacity-unitary-recurrent-neural | 94.1% |
| parallelizing-legendre-memory-unit-training | 98.49% |
| independently-recurrent-neural-network-indrnn | 96% |
| efficiently-modeling-long-sequences-with-1 | 98.70% |
| learning-to-remember-more-with-less | 96.3% |
| a-simple-way-to-initialize-recurrent-networks | 82% |
| r-transformer-recurrent-neural-network | - |
| lipschitz-recurrent-neural-networks | 96.3% |
| unitary-evolution-recurrent-neural-networks | 88% |
| smpconv-self-moving-point-representations-for | 99.10 |