Reproduce “Residual Networks of Residual Networks: Multilevel Residual Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ke Zhang, Miao Sun, Tony X. Han, Xingfang Yuan, Liru Guo, Tao Liu
RoR adds network-level and group-level identity shortcuts while retaining residual-block shortcuts, aiming to ease optimization of very deep image classifiers. On CIFAR-10, a 164-layer RoR-3 trained without stochastic depth reaches 4.86% test error, versus 5.07% for a same-depth ResNet. On CIFAR-100, however, RoR-3 improves over ResNet only with stochastic depth in the reported comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.