Evaluating knowledge transfer and zero-shot learning in a large-scale setting
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1641-1648
- https://doi.org/10.1109/cvpr.2011.5995627
Abstract
While knowledge transfer (KT) between object classes has been accepted as a promising route towards scalable recognition, most experimental KT studies are surprisingly limited in the number of object classes considered. To support claims of KT w.r.t. scalability we thus advocate to evaluate KT in a large-scale setting. To this end, we provide an extensive evaluation of three popular approaches to KT on a recently proposed large-scale data set, the ImageNet Large Scale Visual Recognition Competition 2010 data set. In a first setting they are directly compared to one-vs-all classification often neglected in KT papers and in a second setting we evaluate their ability to enable zero-shot learning. While none of the KT methods can improve over one-vs-all classification they prove valuable for zero-shot learning, especially hierarchical and direct similarity based KT. We also propose and describe several extensions of the evaluated approaches that are necessary for this large-scale study.Keywords
This publication has 19 references indexed in Scilit:
- Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge TransferPublished by Springer Nature ,2012
- Large-scale image classification: Fast feature extraction and SVM trainingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Aggregating local descriptors into a compact image representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- What helps where – and why? Semantic relatedness for knowledge transferPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Learning to detect unseen object classes by between-class attribute transferPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Learning and using taxonomies for fast visual categorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Semantic Hierarchies for Visual Object RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- WordNetCommunications of the ACM, 1995
- Acceleration of Stochastic Approximation by AveragingSIAM Journal on Control and Optimization, 1992