Multimodal Scene Understanding

Chapter 4

Learning Convolutional Neural Networks for Object Detection with Very Little Training Data

Christoph Reinders^⁎; Hanno Ackermann^⁎; Michael Ying Yang^†; Bodo Rosenhahn^{⁎    ⁎}Institute for Information Processing, Leibniz University Hanover, Hanover, Germany^†Scene Understanding Group, University of Twente, Enschede, The Netherlands

Abstract

In recent years, convolutional neural networks have shown great success in various computer vision tasks such as classification, object detection, and scene analysis. These algorithms are usually trained on large datasets consisting of thousands or millions of labeled training examples. The availability of sufficient data, however, limits possible applications. While large amounts of data can be quickly collected, ...