Viet-Anh on Software Logo

What is: Frequency channel attention networks?

SourceFcaNet: Frequency Channel Attention Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

FCANet contains a novel multi-spectral channel attention module. Given an input feature map XRC×H×WX \in \mathbb{R}^{C \times H \times W}, multi-spectral channel attention first splits XX into many parts xiRC×H×Wx^{i} \in \mathbb{R}^{C' \times H \times W}. Then it applies a 2D DCT to each part xix^{i}. Note that a 2D DCT can use pre-processing results to reduce computation. After processing each part, all results are concatenated into a vector. Finally, fully connected layers, ReLU activation and a sigmoid are used to get the attention vector as in an SE block. This can be formulated as: \begin{align} s = F_\text{fca}(X, \theta) & = \sigma (W_{2} \delta (W_{1}[(\text{DCT}(\text{Group}(X)))])) \end{align} \begin{align} Y & = s X \end{align} where Group()\text{Group}(\cdot) indicates dividing the input into many groups and DCT()\text{DCT}(\cdot) is the 2D discrete cosine transform.

This work based on information compression and discrete cosine transforms achieves excellent performance on the classification task.