PaperICML 2015 · 2015
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
1page built on it
0more pages cite it
0narratives
6registry papers cite it
In the Atlas
ConceptPrimary source of
Normalization
Standardises intermediate activations over a chosen index set, then restores capacity with a learned affine transform; batch, layer, instance, and group normalization differ only in which indices are pooled.
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 6
Builds on · 0
Built upon by · 6
2016Layer NormalizationBa, Kiros, Hinton2018Group NormalizationWu, He2019Momentum Contrast for Unsupervised Visual Representation LearningHe, Fan et al.2020A Simple Framework for Contrastive Learning of Visual RepresentationsChen, Kornblith et al.2020Bootstrap your own latent: A new approach to self-supervised LearningGrill, Strub et al.2020PointRend: Image Segmentation As RenderingKirillov, Wu et al.