Timezone: »

Data Augmentation for Meta-Learning
Renkun Ni · Micah Goldblum · Amr Sharaf · Kezhi Kong · Tom Goldstein

Tue Jul 20 09:00 PM -- 11:00 PM (PDT) @ Virtual

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for sampling. In contrast, meta-learning algorithms sample support data, query data, and tasks on each training step. In this complex sampling scenario, data augmentation can be used not only to expand the number of images available per class, but also to generate entirely new classes/tasks. We systematically dissect the meta-learning pipeline and investigate the distinct ways in which data augmentation can be integrated at both the image and class levels. Our proposed meta-specific data augmentation significantly improves the performance of meta-learners on few-shot classification benchmarks.

Author Information

Renkun Ni (University of Maryland)
Micah Goldblum (University of Maryland)
Amr Sharaf (University of Maryland)
Kezhi Kong (University of Maryland, College Park)
Tom Goldstein (University of Maryland)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors