×

SkipNet

swMATH ID: 31369
Software Authors: Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, Joseph E. Gonzalez
Description: SkipNet: Learning Dynamic Routing in Convolutional Networks. 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. We introduce SkipNet, a modified residual network, that uses a gating network to selectively skip convolutional blocks based on the activations of the previous layer. We formulate the dynamic skipping problem in the context of sequential decision making and propose a hybrid learning algorithm that combines supervised learning and reinforcement learning to address the challenges of non-differentiable skipping decisions. We show SkipNet reduces computation by 30-90
Homepage: https://arxiv.org/abs/1711.09485
Source Code:  https://github.com/ucbdrive/skipnet
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Convolutional Network
Related Software: Adam; MixTrain; Marabou; Reluplex; TensorFlow; PaRoT; Cityscapes; obliqueRF; MS-COCO; Fashion-MNIST; PyTorch; C4.5; UCI-ml
Cited in: 1 Publication

Citations by Year