# SkipNet: Learning Dynamic Routing in Convolutional Networks

Xin WangFisher YuZi-Yi DouTrevor DarrellJoseph E. Gonzalez

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input basis... (read more)

PDF Abstract