From: DeConFuse: a deep convolutional transform-based unsupervised fusion framework

Phase | Steps | Time complexity | Dimension description |
---|---|---|---|

Training phase | 1. Convolution layers | \(\mathcal {O}(P_{\ell } D_{\ell } M_{\ell } C)\) | |

2. Fully-connected (f.-c.) layer | \(\mathcal {O}(I^{2} C^{2})\) | \(S^{(c)} \in \mathbb {R}^{K\times D}\) | |

3. Frobenius norm on conv. layers | \(\mathcal {O}\left (P_{\ell } M_{\ell } C\right)\) | \(T_{\ell }^{(c)}\in \mathbb {R}^{P_{\ell }\times M_{\ell }}\) | |

4. Frobenius norm on f.-c. layer | \(\mathcal {O}(I^{2} C^{2})\) | \(\text {flat}(X^{(c)})\in \mathbb {R}^{K\times I}\) | |

5. log-det on conv. layers | \(\mathcal {O}(P_{\ell }^{2} M_{\ell } C)\) | \(\widetilde {T_{c}} \in \mathbb {R}^{I \times O}\) | |

6. log-det on f.-c. layer | \(\mathcal {O}(I^{3}C^{2})\) | ||

Testing phase | Step 1. + Step 2. | Step 1. + Step 2. |