English

Fast Learning and Prediction for Object Detection using Whitened CNN Features

Computer Vision and Pattern Recognition 2017-04-13 v2

Abstract

We combine features extracted from pre-trained convolutional neural networks (CNNs) with the fast, linear Exemplar-LDA classifier to get the advantages of both: the high detection performance of CNNs, automatic feature engineering, fast model learning from few training samples and efficient sliding-window detection. The Adaptive Real-Time Object Detection System (ARTOS) has been refactored broadly to be used in combination with Caffe for the experimental studies reported in this work.

Keywords

Cite

@article{arxiv.1704.02930,
  title  = {Fast Learning and Prediction for Object Detection using Whitened CNN Features},
  author = {Björn Barz and Erik Rodner and Christoph Käding and Joachim Denzler},
  journal= {arXiv preprint arXiv:1704.02930},
  year   = {2017}
}

Comments

Technical Report about the possibilities introduced with ARTOS v2, originally created March 2016

R2 v1 2026-06-22T19:13:03.650Z