S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

Understand

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN).

• In contrast to static methods (e.g.
• weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on "easy" samples while maintaining the overall model performance.
• In this paper, we introduce a general framework, S2DNAS, which can transform various static CNN models to support dynamic inference via neural architecture search.