Transfer Learning

Online Links

  1. OverFeat – a Convolutional Network-based image classifier and feature extractor
    [ MORE ]

Transfer Learning Presentations

  • Riedel, M.: Deep Learning Applications in Science using Transfer Learning, GridKa School Seminar, August 28 – September 1, 2017, Karlsruhe Institute of Technology, Campus North, Karlsruhe, Germany
    [ EVENT ]

    • Abstract: Deep learning models like convolutional neural networks (CNNs) deliver highly accurate results in classification tasks but require large enough data sets and good corresponding labels. However, one key problem in science and engineering is that data sets unfortunately have often only limited labeled data. Using CNNs together with such data sets can be problematic because it can lead to enourmous overfitting thus loosing much of the generalization capability of the model. The talk informs about research methods of using generic representations from deep learning networks that can facilitate transfer learning between different domains in cases where limited amount of labeled data is available. Examples are given in the scientific domain of remote sensing where the availability of labels is scarce and would involve extended efforts and costs for acquiring like performing ground truth campaigns.

Morris Riedel Transfer Learning

Selected OverFeat Facts

  • A Convolutional Network-based image classifier and feature extractor
  • Trained on the ImageNet dataset and participated in the ImageNet 2013 competition
  • It enables researchers to use OverFeat to recognize images and extract Features
  • A library with C++ source code is provided for running the OverFeat convolutional network, together with wrappers in various scripting languages (Python, Lua, etc.)
  • It was trained with the Torch7 neural Network package
  • A whole package is provided with Tools to run the Network in a standalone fashion
  • The training code is not distributed at this time

Selected OverFeat Papers

  1. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks, in arXiv preprint arXiv:1312.6229 (2013),