Supplementary Material for "CLEARER: Multi-Scale Neural Architecture Search for Image Restoration "

In the paper, we present a multi-scale search space which is casted into a differentiable supernet consisting of three modules, i.e., parallel module, transition module, and fusion module. As shown in Figure 1.(a), there are As mentioned in the main body of the paper, the super-network we build for restoration contains three cells and each cell consists of four cascade modules. Namely, there are 12 cascade modules in total. The strided convolution is used to down sample features. The convolutional sequence is arranged in a residual manner for each parallel direction.