Divergent search for image classification behaviors
OA Location
Author(s)
Tan, Jeremy
Kainz, Bernhard
Type
Conference Paper
Abstract
When data is unlabelled and the target task is not known a priori, divergent search offers a strategy for learning a wide range of skills. Having such a repertoire allows a system to adapt to new, unforeseen tasks. Unlabelled image data is plentiful, but it is not always known which features will be required for downstream tasks. We propose a method for divergent search in the few-shot image classification setting and evaluate with Omniglot and Mini-ImageNet. This high-dimensional behavior space includes all possible ways of partitioning the data. To manage divergent search in this space, we rely on a meta-learning framework to integrate useful features from diverse tasks into a single model. The final layer of this model is used as an index into the `archive' of all past behaviors. We search for regions in the behavior space that the current archive cannot reach. As expected, divergent search is outperformed by models with a strong bias toward the evaluation tasks. But it is able to match and sometimes exceed the performance of models that have a weak bias toward the target task or none at all. This demonstrates that divergent search is a viable approach, even in high-dimensional behavior spaces.
Date Issued
2020-07-08
Date Acceptance
2020-07-01
Citation
Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, 2020, pp.91-92
Publisher
ACM
Start Page
91
End Page
92
Journal / Book Title
Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion
Copyright Statement
© 2020 Copyright held by the owner/author.
Source
GECCO '20: Genetic and Evolutionary Computation Conference
Publication Status
Published
Start Date
2020-07-08
Finish Date
2020-07-12
Coverage Spatial
Cancún Mexico
Date Publish Online
2020-07-08