PaperCVPR 2015 · 2015
Going deeper with convolutions
1page built on it
5more pages cite it
2narratives
5registry papers cite it
In the Atlas
ModelPrimary source of
GoogLeNet
Twenty-two-layer CNN built from Inception modules — parallel 1×1, 3×3, 5×5 convolutions and 3×3 max-pool concatenated along the channel axis, with 1×1 bottlenecks reducing dimensionality before the larger spatial convs.
Cited as a reference by 5 pages, grouped by domain
Detection 1
Appears in 2 narratives
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 5
Builds on · 1
2012ImageNet Classification with Deep Convolutional Neural NetworksKrizhevsky, Sutskever, HintonBuilt upon by · 5
2016Deep Residual Learning for Image RecognitionHe, Zhang et al.2016You Only Look Once: Unified, Real-Time Object DetectionRedmon, Divvala et al.2018MobileNetV2: Inverted Residuals and Linear BottlenecksSandler, Howard et al.2019Deep High-Resolution Representation Learning for Human Pose EstimationSun, Xiao et al.2020A Simple Framework for Contrastive Learning of Visual RepresentationsChen, Kornblith et al.