Hierarchical zero-shot classification with convolutional neural network features and semantic attribute learning

Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I. Jeng Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We examine hierarchical approaches to image classification problems that include categories for which we have no training examples. Building on prior work in hierarchical classification that optimizes the trade-off between depth in a tree and accuracy of placement, we compare the performance of multiple formulations of the problem on both previously seen (non-novel) and previously unseen (novel) classes. We use a subset of 150 object classes from the ImageNet ILSVRC2012 data set, for which we have 218 human-annotated semantic attribute labels and for which we compute deep convolutional features using the OVERFEAT network. We quantitatively evaluate several approaches, using input posteriors derived from distances to SVM classifier boundaries as well as input posteriors based on semantic attribute estimation. We find that the relative performances of the methods differ in non-novel and novel applications and achieve information gains in novel applications through the incorporation of attribute-based posteriors.

Original languageEnglish (US)
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages194-197
Number of pages4
ISBN (Electronic)9784901122160
DOIs
StatePublished - Jul 19 2017
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: May 8 2017May 12 2017

Publication series

NameProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
CountryJapan
CityNagoya
Period5/8/175/12/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Hierarchical zero-shot classification with convolutional neural network features and semantic attribute learning'. Together they form a unique fingerprint.

Cite this