Learning from Random Subspace Exploration: Generalized Test-Time Augmentation with Self-supervised Distillation

TL;DR

The paper proposes Generalized Test-Time Augmentation (GTTA), a versatile method that enhances model performance across various tasks by generating diverse augmented samples through PCA perturbations and reduces test-time costs via self-supervised distillation.

Contribution

It introduces a general, off-the-shelf TTA method applicable to multiple domains, with a novel PCA-based augmentation and a self-supervised training stage to improve efficiency.

Findings

GTTA improves accuracy across multiple vision and non-vision tasks.

The method reduces test-time computational costs significantly.

GTTA demonstrates effectiveness on a new underwater salmon dataset.

Abstract

We introduce Generalized Test-Time Augmentation (GTTA), a highly effective method for improving the performance of a trained model, which unlike other existing Test-Time Augmentation approaches from the literature is general enough to be used off-the-shelf for many vision and non-vision tasks, such as classification, regression, image segmentation and object detection. By applying a new general data transformation, that randomly perturbs multiple times the PCA subspace projection of a test input, GTTA creates valid augmented samples from the data distribution with high diversity, properties we theoretically show that are essential for a Test-Time Augmentation method to be effective. Different from other existing methods, we also propose a final self-supervised learning stage in which the ensemble output, acting as an unsupervised teacher, is used to train the initial single student model, thus reducing significantly the test time computational cost. Our comparisons to strong TTA approaches and SoTA models on various vision and non-vision well-known datasets and tasks, such as image classification and segmentation, pneumonia detection, speech recognition and house price prediction, validate the generality of the proposed GTTA. Furthermore, we also prove its effectiveness on the more specific real-world task of salmon segmentation and detection in low-visibility underwater videos, for which we introduce DeepSalmon, the largest dataset of its kind in the literature.