Sliding window protocol

Deep learning

Pattern recognition (psychology)

Process engineering

Feature (linguistics)

Bounding overwatch

Operating system

Image (mathematics)

Extractor

Machine learning

Minimum bounding box

Engineering

Philosophy

Artificial intelligence

Systems engineering

Object detection

Window (computing)

Computer science

Linguistics

Task (project management)

Feature extraction

Convolutional neural network

arXiv (Cornell University)

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 learned 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 obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks