Table 2 Comparison of computational complexity of estimation methods. In the 1 st line (Setting) ‘High density’ and ‘Low density’ mean high and low density pilot datasets, respectively.
From: Joint channel estimation and feedback with masked token transformers in massive MIMO systems
Setting | High density | Low density |
|---|---|---|
Method | FLOPs/Params | FLOPs/Params |
ChannelNet | 2.59G/0.194M | 2.59G/0.194M |
Attention-Aid | 2.25G/0.169M | 2.25G/0.169M |
AttentionNet | 3.95G/5.29M | 9.12G/5.28M |
CBDNet | 7.76G/4.33M | 7.76G/4.33M |
OursEstimation | 1.18G/5.30M | 1.04G/5.30M |
