ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices · HackerPapers discussions

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices — HN submission

Fri, 12 Jan 2018 05:35:47 GMT

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile [pdf]

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices — mentioned by tanilama

Tue, 14 Nov 2017 07:25:52 GMT

https://arxiv.org/abs/1512.03385 Deep Residual Learning for Image Recognition Citation 4000+. Milestone of image recognition. https://arxiv.org/abs/1502.01852 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Also known as PreLU, citation 1600+. The initialization scheme is widely adapted by a lot of following works. Those are the most influential ones, all come from Kaiming He. He is now in FAIR, and keeps very good publication record, with works like MASK-RCNN, but that doesn't really count as purely Chinese contribution, so we skipped here. Some…

Paper and discussion history. A mention is not an endorsement.

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices — mentioned by bwasti

Sun, 23 Jul 2017 21:32:08 GMT

I doubt pruning alone is going to serve up the same kind of wins that energy aware architectures will. The main problem is that convolutions are heavy computational operations. There has been ongoing research in modifications to the convolution that basically decrease the amount of computation being done in channel space (grouped and depthwise separable convolutions). The tradeoff is accuracy, but new techniques (like shuffling the channels) are helping recover that. MobileNets and ShuffleNet are some examples. They see 10x reductions in MACs, far more than the "73 percent reduction in power…

Paper and discussion history. A mention is not an endorsement.