PaperNeurIPS · 2012
ImageNet Classification with Deep Convolutional Neural Networks
2pages built on it
5more pages cite it
2narratives
10registry papers cite it
In the Atlas
ModelPrimary source of
AlexNet
Eight-layer convolutional neural network for 1000-class image classification on ImageNet, trained end-to-end on two GPUs with ReLU activations, local response normalisation, overlapping max-pooling, and dropout; the first deep CNN to win ILSVRC by a large margin.
ConceptPrimary source of
Convolutional Neural Network
A feed-forward network that builds a spatial hierarchy of learned features by alternating weight-shared convolution layers, pointwise nonlinearities, and spatial downsampling, trained end-to-end by backpropagation.
Cited as a reference by 5 pages, grouped by domain
Detection 1
Image formation 1
Appears in 2 narratives
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 10
Builds on · 0
Built upon by · 10
2014Very Deep Convolutional Networks for Large-Scale Image RecognitionSimonyan, Zisserman2015Distilling the Knowledge in a Neural NetworkHinton, Vinyals, Dean2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksRen, He et al.2015Going deeper with convolutionsSzegedy, Liu et al.2016Deep Residual Learning for Image RecognitionHe, Zhang et al.2017Focal Loss for Dense Object DetectionLin, Goyal et al.2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic SegmentationYu, Wang et al.