Sequential Image Classification On Sequential

评估指标

Permuted Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
SMPConv	99.10	SMPConv: Self-moving Point Representations for Continuous Convolution
LSSL	98.76%	Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
FlexTCN-4	98.72%	FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
S4	98.70%	Efficiently Modeling Long Sequences with Structured State Spaces
CKCNN (1M)	98.54%	CKConv: Continuous Kernel Convolution For Sequential Data
Modified LMU (165k)	98.49%	Parallelizing Legendre Memory Unit Training
UnICORNN	98.4	UnICORNN: A recurrent model for learning very long time dependencies
HiPPO-LegS	98.3%	HiPPO: Recurrent Memory with Optimal Polynomial Projections
CKCNN (100k)	98%	CKConv: Continuous Kernel Convolution For Sequential Data
ODE-LSTM	97.83%	Learning Long-Term Dependencies in Irregularly-Sampled Time Series
coRNN	97.34%	Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies
Temporal Convolutional Network	97.2%	An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Dense IndRNN	97.2%	Deep Independently Recurrent Neural Network (IndRNN)
LMU	97.2%	Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks	-
Adaptive-saturated RNN	96.96%	Adaptive-saturated RNN: Remember more with less instability	-
Sparse Combo Net	96.94	RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks
GAM-RHN-1	96.8%	Recurrent Highway Networks with Grouped Auxiliary Memory	-
LEM	96.6%	Long Expressive Memory for Sequence Modeling
DNC+CUW	96.3%	Learning to Remember More with Less Memorization
LipschitzRNN	96.3%	Lipschitz Recurrent Neural Networks

0 of 30 row(s) selected.