Viet-Anh on Software Logo

What is: Cycle Consistency Loss?

SourceUnpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Cycle Consistency Loss is a type of loss used for generative adversarial networks that performs unpaired image-to-image translation. It was introduced with the CycleGAN architecture. For two domains XX and YY, we want to learn a mapping G:XYG : X \rightarrow Y and F:YXF: Y \rightarrow X. We want to enforce the intuition that these mappings should be reverses of each other and that both mappings should be bijections. Cycle Consistency Loss encourages F(G(x))xF\left(G\left(x\right)\right) \approx x and G(F(y))yG\left(F\left(y\right)\right) \approx y. It reduces the space of possible mapping functions by enforcing forward and backwards consistency:

L_cyc(G,F)=E_xp_data(x)[F(G(x))x_1]+E_yp_data(y)[G(F(y))y_1]\mathcal{L}\_{cyc}\left(G, F\right) = \mathbb{E}\_{x \sim p\_{data}\left(x\right)}\left[||F\left(G\left(x\right)\right) - x||\_{1}\right] + \mathbb{E}\_{y \sim p\_{data}\left(y\right)}\left[||G\left(F\left(y\right)\right) - y||\_{1}\right]