computer-vision   1633

« earlier    

[1901.08971] FaceForensics++: Learning to Detect Manipulated Facial Images
The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns on the implication on the society. At best, this leads to a loss of trust in digital content, but it might even cause further harm by spreading false information and the creation of fake news. In this paper, we examine the realism of state-of-the-art image manipulations, and how difficult it is to detect them - either automatically or by humans. In particular, we focus on DeepFakes, Face2Face, and FaceSwap as prominent representatives for facial manipulations. We create more than half a million manipulated images respectively for each approach.
facial-recognition  fake-news  machine-learning  computer-vision  research-papers  synthetic-media 
15 days ago by lavallee
[1701.01370] Learning from Synthetic Humans
Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL (Synthetic hUmans foR REAL tasks): a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.
computer-vision  synthetic-data  dreaming-about-people  training-data  data-generation  rather-interesting  to-write-about  pose-estimation  image-segmentation 
16 days ago by Vaguery
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet | OpenReview
"Deep Neural Networks (DNNs) excel on many complex perceptual tasks but it has proven notoriously difficult to understand how they reach their decisions. We here introduce a high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain. Our model, a simple variant of the ResNet-50 architecture called BagNet, classifies an image based on the occurrences of small local image features without taking into account their spatial ordering. This strategy is closely related to the bag-of-feature (BoF) models popular before the onset of deep learning and reaches a surprisingly high accuracy on ImageNet (87.6% top-5 for 32 x 32 px features and Alexnet performance for 16 x16 px features). The constraint on local features makes it straight-forward to analyse how exactly each part of the image influences the classification. Furthermore, the BagNets behave similar to state-of-the art deep neural networks such as VGG-16, ResNet-152 or DenseNet-169 in terms of feature sensitivity, error distribution and interactions between image parts. This suggests that the improvements of DNNs over previous bag-of-feature classifiers in the last few years is mostly achieved by better fine-tuning rather than by qualitatively different decision strategies."
deep-learning  convnet  computer-vision  bagnet  imagenet 
18 days ago by arsyed

« earlier    

related tags

2016  3d  action-recognition  activity-recognition  agenda  ai  algorithm  algorithms  animation  api  application  ar  articles  autonomous_vehicles  bagnet  barcode  biometrics  blender  blog  book-list  book  camera  captcha  chars74k  chrictonesque  cnn  cnns  coco  conference  convnet  convolution-neural-networks  cool  cs231n-2018  cs231n  css  cv  data-generation  datasets  deep-learning  deeplearning  dev  dialog-system  dreaming-about-people  drones  embedded  evaluation-measures  evaluation  explanation  face_recognition  facebook  facial-recognition  fake-news  gans  gaze  gender  go  golang  google  graphics  hardware  icdar  ifttt  image-classification  image-labeling  image-saliency  image-segmentation  image  image_analysis  imagenet  images  information  inspiration  intel  internet-of-things  intersection-over-union  iot  iou  kaggle  learning  library  list  machine-learning  machine_learning  machinelearning  market-intelligence  mathematics  meshroom  miou  ml  multimedia  natural-user-interfaces  netflix  neural-net  neuroscience  nlp  node.js  notebook  ocr  opencv  opensource  paper  papers  pascal  people  photo  photogrametry  photogrammetric  photography  pix2pix  pose-estimation  prejudice  programming  python  quickdraw  raspberrry-pi  raspberry-pi  raspberrypi  rather-interesting  recognition  reconstruction  reinforcement-learning  report  research-papers  research  resource  robotics  salt  scanner  security  selection  sensors  serverless  signal-processing  software  stereo-vision  stereo  stupidity  surveillance  surveys  synthetic-data  synthetic-media  talks  tensorflow.js  tensorflow  thumbail  time-series  to-write-about  tools  training-data  trends2018  tutorial  university-ad-hoc  video  visualization  vr  web  winner 

Copy this bookmark: