OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Michael Mathieu, Yann LeCun, Rob Fergus, David Eigen, Pierre Sermanet, Xiang Zhang

Dec 24, 2013 (modified: Dec 24, 2013) ICLR 2014 conference submission readers: everyone
  • Decision: submitted, no decision
  • Abstract: We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learnt simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013), and produced near state of the art results for the detection and classifications tasks. Finally, we release a feature extractor from our best model called OverFeat.