Deep Residual Learning for Image Recognition
ResNet, 'Deep Residual Learning for Image Recognition' 입니다.
ResNet은 residual repesentation 함수를 학습함으로써 신경망이 152 layer까지 가질 수 있습니다. ResNet은 이전 layer의 입력을 다음 layer로 전달하기 위해 skip connection(또는 shorcut connection)을 사용합니다. 이 skip connection은 깊은 신경망이 가능하게 하고 ResNet은 ILSVRC 2015 우승을 했습니다.
Abstract
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Documentation
- Deep Residual Learning for Image Recognition
- https://arxiv.org/abs/1512.03385