Closed NorbertZheng closed 1 year ago
In this story, RiR (ResNet in ResNet) is briefly reviewed. RiR attempts to generalize the ResNet block for Residual Network by
so as to improve the accuracy. And it is published in 2016 arXiv with about 80 citations. I treat RiR as a kind of sidetrack papers for ResNet.
RiR is designed in the way that the input signal can go through the network in between ResNet and standard ConvNet.
A generalized residual architecture is introduced to combines residual networks and standard convolutional networks in parallel residual and non-residual streams. (a) 2-layer ResNet block. (b) 2 generalized residual blocks (ResNet Init). (c) 2-layer ResNet block from 2 generalized residual blocks (grayed-out connections are 0). (d) 2-layer RiR block.
Below table summarized the conditions when residual and transient connections are on/off: The 18-layer + wide RiR used for experiments: 18-layer + wide RiR.
CIFAR-10.
CIFAR-100.
Accuracy Change When Zeroing Learned Connections of One Layer in Each Stream.
Accuracy When Adding More Layers Within a Residual Block.
Accuracy of RiR and ResNet with different numbers of layers per block on CIFAR-10.
Number of Blocks and Layers Per Block.
Besides RiR, there is also another sidetrack paper, ResNet of ResNet (RoR), firstly appeared in 2016 arXiv, and recently published in 2018 TCSVT. Hope I can cover it in the future.
Sik-Ho Tang. Review: RiR — ResNet in ResNet (Image Classification).