Deep Residual Learning for Image Recognition

jixiaohui 2018-01-10 11:15
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 re

A Neural Algorithm of Artistic Style

dwSun 2018-02-07 17:07
In fine art, especially painting, humans have mastered the skill to create unique visual experiences through composing a complex interplay between the content and style of an image. Thus far the algor

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

jixiaohui 2018-01-10 11:37
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve ve

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

辉仔 2018-01-10 10:49
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the trai

Going Deeper with Convolutions

辉仔 2018-01-10 11:12
We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Sca

Very Deep Convolutional Networks for Large-Scale Image Recognition

辉仔 2018-01-10 10:31
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of in

Mask R-CNN

dwSun 2018-01-15 20:45
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality

Learning Transferable Architectures for Scalable Image Recognition

jixiaohui 2018-01-10 15:36
Developing neural network image classification models often requires significant architecture engineering. In this paper, we attempt to automate this engineering process by learning the model architec

Fully Convolutional Networks for Semantic Segmentation

辉仔 2018-01-10 10:46
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-a

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

jixiaohui 2018-01-10 14:52
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to