Evaluating knowledge transfer and zero-shot learning in a large-scale setting
Citations Over TimeTop 1% of 2011 papers
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.
Related Papers
- → Physical and Information Theoretical Limits of the Single-Shot 3D Movie Camera(2019)2 cited
- → 3‐D prestack depth migration with single‐shot and synthesized‐shot records(2002)2 cited
- Nosocomial infection in gun-shot [correction of gut-shot] injury patient: a case report.(1998)
- → Birdman"s Single Shot Effect : Realist Aesthetics and the Illusion(2016)
- Birdman's Single Shot Effect: Realist Aesthetics and the Illusion(2016)