deeplearning   11117

« earlier    

[1506.02640] You Only Look Once: Unified, Real-Time Object Detection
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.
Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.
papers  cv  deeplearning 
6 hours ago by jblocksom
YOLO: Real-Time Object Detection
You only look once (YOLO) is a state-of-the-art, real-time object detection system
deeplearning  cv 
6 hours ago by jblocksom
We're seeing an optimization of chips and hardware to take advantage of architectures. This space is…
deeplearning  from twitter
9 hours ago by neuralmarket
Top 5 Data Science & Machine Learning Repositories on GitHub in Jan 2018
Top 5 Data Science & Machine Learning Repositories on GitHub in Jan 2018 , machinelearning
deeplearning  from twitter
18 hours ago by jxstanford
RT : All the matrix you need for has been conveniently packaged & clarified for you by…
calculus  deeplearning  from twitter_favs
19 hours ago by hustwj
Overview of Udacity Artificial Intelligence Engineer Nanodegree, Term 2
After finishing a first term of the Artificial Intelligence Nanodegree I enrolled into the second term with a clear expectation to learn more about deep neural networks and, particularly, about…
23 hours ago by carlosviansi
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 
yesterday by ianchanning
applied to rhythms allowed researchers to differentiate Females and Males just by analysing t…
brain  DeepLearning  from twitter_favs
yesterday by danbri

« earlier    

related tags

2012  2017  ai  anti  architecture  archive  autism  autonomous  avoidance  basics  bayesian  bigdata  bioinformatics  blogs  book  brain  c++  calculus  camera  chollet  cinematography  class  classification  cloudcomputing  cnn  cocish  computerscience  computervision  computing  content-based  course  courses  cs  cv  datascience  datasets  dataviz  deep-learning  deep  deepreinforcementlearning  deployment  derivatives  design  disambiguation  dl  drone  embedding  encryption  entity  explainable  face  facialrecognition  favorite  flight  gan  gender  generative  gpu  graph  healthcare  howto  ifttt  image  imageprocessing  images  inspiration  interpretability  iot  javascript  kaggle  keras  learning  linkfodder  lstm  machine-learning  machine  machinelearning  math  matrix  mit  ml  music  network  neuralnets  neuralnetworks  nlp  nn  obstacle  online  opensource  optics  optik  optimization  paper  papers  patrickwinston  performance  photo  physik  presentations  programming  python  pytorch  quadrotor  r  randomforest  randomforests  recap  recognition  recommendations  research  rl  rnn  rstudio  rstudioconf  search  signalprocessing  software  statistics  survey  tensorflow  theory  tips  torch  tutorial  twitter  understanding  video  vision  visualization  wikipedia  wordvectors 

Copy this bookmark: