Deep Residual Learning for Image Recognition

by   Kaiming He, et al.

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 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 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.


Residual CNDS

Convolutional Neural networks nowadays are of tremendous importance for ...

Improved Residual Networks for Image and Video Recognition

Residual networks (ResNets) represent a powerful type of convolutional n...

Deep Residual Networks with Exponential Linear Unit

Very deep convolutional neural networks introduced new problems like van...

Faster Training of Very Deep Networks Via p-Norm Gates

A major contributing factor to the recent advances in deep neural networ...

Aggregated Residual Transformations for Deep Neural Networks

We present a simple, highly modularized network architecture for image c...

Training Deeper Convolutional Networks with Deep Supervision

One of the most promising ways of improving the performance of deep conv...

Depth and Representation in Vision Models

Deep learning models develop successive representations of their input i...

Code Repositories


Deep Residual Learning for Image Recognition

view repo


Torch implementation of ResNet from and training scripts

view repo


This is a Torch implementation of ["Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun]( the winners of the 2015 ILSVRC and COCO challenges.

view repo


THE Deep Learning Benchmarks

view repo


Recreating the Deep Residual Network in Lasagne

view repo

Please sign up or login with your details

Forgot password? Click here to reset