The ISC is part of the Johns Hopkins Applied Physics Laboratory and will follow all current policies. Please visit the JHU/APL page for more information on the Lab's visitor guidance.

2017

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


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.

Citation

@inproceedingsMarkowitz_2017 doi: 10.23919/mva.2017.7986834 url: https://doi.org/10.23919/mva.2017.7986834 year: 2017 month: may publisher: IEEE author: Markowitz Jared and Schmidt Aurora C. and Burlina Philippe M. and Wang I-Jeng title: Hierarchical zero-shot classification with convolutional neural network features and semantic attribute learning booktitle: 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA)

Citation

@inproceedingsMarkowitz_2017 doi: 10.23919/mva.2017.7986834 url: https://doi.org/10.23919/mva.2017.7986834 year: 2017 month: may publisher: IEEE author: Markowitz Jared and Schmidt Aurora C. and Burlina Philippe M. and Wang I-Jeng title: Hierarchical zero-shot classification with convolutional neural network features and semantic attribute learning booktitle: 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA)