Data augmentation with mixtures of max-entropy transformations for filling-level classification
We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification. In such a task, properties such as shape or transparency of test-time containers (cup or drinking glass) may differ from those represented in the training data. Dealing with such distribution shifts using standard augmentation schemes is challenging and transforming the training images to cover the properties of the test-time instances requires sophisticated image manipulations. We therefore generate diverse augmentations using a family of max-entropy transformations that create samples with new shapes, colors and spectral characteristics. We show that such a principled augmentation scheme, alone, can replace current approaches that use transfer learning or can be used in combination with transfer learning to improve its performance.
WOS:000918827600315
2022-01-01
978-90-827970-9-1
New York
European Signal Processing Conference
1606
1610
REVIEWED
Event name | Event place | Event date |
Belgrade, SERBIA | Aug 29-Sep 02, 2022 | |