Divergent search for image classification behaviors
Tan J, Kainz B (2020)
Publication Type: Conference contribution
Publication year: 2020
Publisher: Association for Computing Machinery, Inc
Pages Range: 91-92
Conference Proceedings Title: GECCO 2020 Companion - Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion
Event location: Cancun, MEX
ISBN: 9781450371278
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.
Authors with CRIS profile
Involved external institutions
United Kingdom (GB)How to cite
APA:
Tan, J., & Kainz, B. (2020). Divergent search for image classification behaviors. In GECCO 2020 Companion - Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion (pp. 91-92). Cancun, MEX: Association for Computing Machinery, Inc.
MLA:
Tan, Jeremy, and Bernhard Kainz. "Divergent search for image classification behaviors." Proceedings of the 2020 Genetic and Evolutionary Computation Conference, GECCO 2020, Cancun, MEX Association for Computing Machinery, Inc, 2020. 91-92.
BibTeX: Download