Paper2016
Identity Mappings in Deep Residual Networks
He et al.
Pre-activation ResNet design that enables training of 1000+ layer networks
5 entries / Filter in the index →
Paper2016
He et al.
Pre-activation ResNet design that enables training of 1000+ layer networks
Misc2015
Stanford
Stanford's foundational course on deep learning for computer vision
Paper2015
Yu & Koltun
Expanding receptive fields exponentially without losing resolution or adding parameters