Single-path NAS

Single-Path NAS is a convolutional neural network architecture discovered through the Single-Path neural architecture search approach. The NAS utilises a single-path search space. Specifically, compared to previous differentiable NAS methods, Single-Path NAS uses one single-path over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters. The approach is built upon the observation that different candidate convolutional operations in NAS can be viewed as subsets of a single superkernel. Without having to choose among different paths/operations as in multi-path methods, we instead solve the NAS problem as finding which subset of kernel weights to use in each ConvNet layer. By sharing the convolutional kernel weights, we encode all candidate NAS operations into a single superkernel.

The architecture itself uses the inverted residual block from MobileNetV2 as its basic building block.