ImageNet Classification with Deep Convolutional Neural Networks

Alex KrizhevskyIlya SutskeverGeoffrey E. Hinton

   Papers with code   Abstract  PDF

We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 39.7\% and 18.9\% which is considerably better than the previous state-of-the-art results... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
D2Det
(ResNet101-DCN)
0.469
0.469
2
D2Det
(ResNet101)
0.449
0.449
3
D2Det
(ResNet50)
0.437
0.437