Data augmentation with mixtures of max-entropy transformations for filling-level classification

TL;DR

This paper introduces a novel data augmentation method using max-entropy transformations to improve content-level classification under distribution shifts, effectively replacing or complementing transfer learning.

Contribution

The authors propose a principled augmentation scheme based on max-entropy transformations that generate diverse training samples with new shapes, colors, and spectral features.

Findings

Augmentation alone can match transfer learning performance.

Combining augmentation with transfer learning enhances accuracy.

The method effectively handles distribution shifts in test data.

Abstract

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.