cnn   8740

« earlier    

Can you vaccinate yourself against cancer? | CNN
The thought of a vaccine might conjure up memories of that flu shot you get each year, or taking your kids to get their immunizations against polio or measles. Cancer rarely comes to mind when most people think of vaccines, but that appears to be changing. Dr. Seth Pollack, acting instructor of medicine at the UW, is quoted.
Pollack.Seth  UW:Medicine  CNN  cancer  !UWitM  2018  natl 
3 days ago by uwnews
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a \emph{per-pixel} loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing \emph{perceptual} loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results.
imageprocessing  deeplearning  CNN  AI  images  research  paper  styletransfer  algorithms 
3 days ago by sachaa
A Closed-form Solution to Photorealistic Image Stylization
Photorealistic image style transfer algorithms aim at stylizing a content photo using the style of a reference photo with the constraint that the stylized photo should remains photorealistic. While several methods exist for this task, they tend to generate spatially inconsistent stylizations with noticeable artifacts. In addition, these methods are computationally expensive, requiring several minutes to stylize a VGA photo. In this paper, we present a novel algorithm to address the limitations. The proposed algorithm consists of a stylization step and a smoothing step. While the stylization step transfers the style of the reference photo to the content photo, the smoothing step encourages spatially consistent stylizations. Unlike existing algorithms that require iterative optimization, both steps in our algorithm have closed-form solutions. Experimental results show that the stylized photos generated by our algorithm are twice more preferred by human subjects in average. Moreover, our method runs 60 times faster than the state-of-the-art approach.
AI  deeplearning  cnn  research  paper  images  generative  imageprocessing  tweetit  styletransfer 
4 days ago by sachaa
Emma Gonzalez "We call BS"
Powerful speaking skills from her. I wish she hadn't gone down mental illness route — I think that's an easy and dangerous path when we should stand on no one needing these guns. At the same time I don't know if that's the only way we can get something to stop these weapons from being sold.
highschool  guncontrol  nra  speech  video  cnn  gop  politics 
6 days ago by UltraNurd
Emma Gonzalez "We call BS"
Powerful speaking skills from her. I wish she hadn't gone down mental illness route — I think that's an easy and dangerous path when we should stand on no one needing these guns. At the same time I don't know if that's the only way we can get something to stop these weapons from being sold.
politics  highschool  speech  cnn  nra  guncontrol  video  gop 
6 days ago by UltraNurd
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky, University of Toronto
Ilya Sutskever, University of Toronto
Geoffrey E. Hinton, University of Toronto
neuralnetworks  deeplearning  research  papers  cnn  2012 
6 days ago by ianchanning

« earlier    

related tags

!uwitm  2012  2018  accelerator  activelearning  advertising  ai  alexnet  algorithm  algorithms  alibaba  alternative  american-women-documentary-series  analysis  antarctica  apple  applied.physics.laboratory  architecture  arm  art  astley.susan  attention  autoencoder  bangladesch  beme  bike  bloomberg  brooke-baldwin  business  cancer  char  classification  climate.change  college:engineering  college:environment  computer-vision  computervision  computing  conference  content  control  convolution  convolutional  convolutions  course  cv  damon-young  data  datasets  decision  deep-learning  deep  deep_learning  deepface  deeplearning  defect  design  dl  domingos.pedro  donaldtrump  drone  earbuds  embedded  embedding  engagement  entityextraction  evolutionary  face-recognition  facebook  facenet  fakenews  fast-r-cnn  fastai  faster-r-cnn  feed  feminism  financialregulation  florida  flow  foles  football  gcn  generative  genre  gobat.jason  gop  gopro  graph  growth  guncontrol  hall  handelszeitung  health  highschool  history  huffingtonpost  illustration  imageprocessing  imagerecognition  images  inception  intepretable  interpretability  intuition  intuitions  issues  keras  keyword-spotting  learning  lee.craig  lenet-5  list  live  lstm  machine_learning  machinecomprehension  machinelearning  manheim.lisa  marketing  marriage  max-pooling  maxpooling  mediabias  memnn  memory  mir  ml  mobile  model  music  natl  ner  network-in-network  network  neural-network  neural  neuralnetwork  neuralnetworks  news  newsindustry  nlp  nn-architecture  nn-design  nn  nomination  nominations  nra  nyt  obamafailures  object-detection  oci  opencv  opensource  opinion.analysis  optical  optimisation  oscar  oscars  paper  papers  pederson  peoplenow  performance  politics  pollack.seth  r-cnn  rape  readit  real-time  recnn  recursive  regional-proposal  research  resnet  review  rl  rnn  sarah-huny-young  school:law  school:oceanography  search  sentiment  server  socialnetwork  speech  startup  steering  style  styletransfer  sunrise  superbowl  survey  svm  tedium  tensorflow  terrorism  text  textanalysis  theory  tictoc  topics  town  transfer  transferlearning  translate  translation  tree  trump  tv  tweetit  twitter  uk  uw:medicine  very-smart-brothas  vgg-16  video  vikings  visual  visualization  vs  washingtonpost  women  word  yolo 

Copy this bookmark: