Deep Residual Learning for Image Recognition

CVPR 2016 Kaiming HeXiangyu ZhangShaoqing RenJian Sun

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... (read more)

PDF Abstract


Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Image Classification CIFAR-10 ResNet Percentage correct 93.57 # 28
Image Classification CIFAR-10 ResNet Percentage error 6.43 # 14
Object Detection COCO Faster R-CNN + box refinement + context + multi-scale testing Bounding Box AP 34.9 # 34
Object Detection PASCAL VOC 2007 ResNet-101 MAP 76.4% # 10