computervision   4445

« earlier    

The Bitter Lesson
The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin.
computers  ai  machinelearning  algorithms  computervision  deeplearning  games  go  research  academia 
4 days ago by pozorvlak
An open source library for face detection in images. The face detection speed can reach 1500FPS.
computervision  opencv  ml  machinelearning 
8 days ago by Z303
[1902.00236] Natural and Adversarial Error Detection using Invariance to Image Transformations
We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur unintentionally ("natural errors"), or due to intentional adversarial attacks ("adversarial errors"), both in a single unified framework. Our approach is based on the observation that correctly classified images tend to exhibit robust and consistent classifications under certain image transformations (e.g., horizontal flip, small image translation, etc.). In contrast, incorrectly classified images (whether due to adversarial errors or natural errors) tend to exhibit large variations in classification results under such transformations. Our approach does not require any modifications or retraining of the classifier, hence can be applied to any pre-trained classifier. We further use state of the art targeted adversarial attacks to demonstrate that even when the adversary has full knowledge of our method, the adversarial distortion needed for bypassing our detector is no longer imperceptible to the human eye. Our approach obtains state-of-the-art results compared to previous adversarial detection methods, surpassing them by a large margin.
adversarialexamples  ComputerVision  NeuralNetworks  DeepLearning 
12 days ago by csantos
ImageNet | Image Database for Research & Machine Learning
ImageNet is an image database organized according to the WordNet hierarchy (currently only the nouns), in which each node of the hierarchy is depicted by hundreds and thousands of images. Currently we have an average of over five hundred images per node. We hope ImageNet will become a useful resource for researchers, educators, students and all of you who share our passion for pictures.
database  image  images  machinelearning  wordnet  photo  photos  graphic  repository  resource  research  ML  synset  dataset  searchengine  AI  automation  artificialintelligence  training  objectrecognition  recognition  computervision 
13 days ago by csaper
RT : I think what you see probably depends on its rotation for human viewers too…

AI  ComputerVision  from twitter
14 days ago by tonys

« earlier    

related tags

2018  3d  academia  academic  aclu  adversarialexamples  advertising  agriculture  ai  alexa  algorithms  amazon  amber  animation  app  apple  application  art  artificialintelligence  artwork  audio  augmented_reality  automation  aws  azure  bbc  behavioural  bias  bio  biomorph  boats  books  brand  business  by:joshtenebaum  c++  c  calibration  camera  camouflage  cg  challenge  china  civilwar  clarifai  classification  classroom  cloud  clud  cmu  cnn  color  colour  company  computationalphotography  computer  computer_vision  computergraphics  computers  computerscience  computervisionconsulting  concentration  counterexample  cplusplus  crowdsourcing  cv  data  database  datascience  dataset  datasets  deeplearning  design  detection  device  downlinking  ducks  economics  edge  education  eff  embedded  embedding  energy  evolution  example  excel  explainer  explanation  exploration  extraction  face-detection  face-recognition  face  face_recognition  faceapi  facebook  facedetection  faces  facialrecognition  fairness  farming  fashion  fatml  fauxtomation  follow  francescomarconi  fugitive  fulfillment  furniture  future  ga  games  gan  genealogy  geometry  github  glasses  go  google  googlelens  government  gpu  grait  graphic  graphics  hardware  haskell  history  honeywell  hotel  howto  ibm  image  imageprocessing  imagerecognition  images  imaging  immigration  influence  informationweek  interaction  interactive  interface  internet  internetofthings  interpretability  iot  journalism  joybuolamwini  ki  labor  languages  lawenforcement  learning  library  licenseplate  lifeimitatessf  lockheedmartin  logistics  lstm  machine-learning  machine-vision  machine_learning  machinelearning  macos  manga  manipulation  mannequin  mannequinchallenge  maps  mashup  math  mechanicalturk  medium  meme  mesh  michelleobama  microsoft  military  ml  mmist  mobile  motion  ms  msdyn365  neuralnets  neuralnetwork  neuralnetworks  neuralnetworls  nlp  objectmanipulation  objectrecognition  oceans  oil  opencv  oprah  orcam  oregon  outsourcing  paper  patternrecognition  pcl  people  peopletofollow  performance  photo  photography  photos  point  police  politics  pose  posedetection  powerapp  prediction  press  privacy  programming  puppeteering  python  pytorch  raccoon  raspberrypi  raykurzweil  readers  realestate  realtime  recognition  reconstruction  regualation  rekognition  repository  research  resource  retail  rgbd  rnn  robotics  robots  satellite  science  searchengine  segmentation  server  shared  smarthome  smartphone  socialmedia  solarpanels  space  spreadsheet  stanford  style  surveillance  synset  technology  tensorflow  tetris  text  text_detection  text_localization  texty  tinmitgebru  tools  towatch  tracking  tradingbot  training  trainingsets  translation  trends  tutorial  tutorials  ukraine  users  verizon  video  videorecognition  virtual  vision  visualcommonsense  visualization  voice  weapon  wordnet  writing  wsj  youtube 

Copy this bookmark: