Viet-Anh on Software Logo

What is: Concatenation Affinity?

SourceNon-local Neural Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Concatenation Affinity is a type of affinity or self-similarity function between two points x_i\mathbb{x\_{i}} and x_j\mathbb{x\_{j}} that uses a concatenation function:

f(x_i,x_j)=ReLU(wT_f[θ(x_i),ϕ(x_j)]) f\left(\mathbb{x\_{i}}, \mathbb{x\_{j}}\right) = \text{ReLU}\left(\mathbb{w}^{T}\_{f}\left[\theta\left(\mathbb{x}\_{i}\right), \phi\left(\mathbb{x}\_{j}\right)\right]\right)

Here [,]\left[·, ·\right] denotes concatenation and w_f\mathbb{w}\_{f} is a weight vector that projects the concatenated vector to a scalar.