Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation

TL;DR

This paper introduces an adaptive sensitivity-guided augmentation method that significantly improves the robustness of image segmentation models against natural corruptions, with faster analysis and practical on-the-fly application during training.

Contribution

It presents a novel, efficient sensitivity analysis approach that enables real-time, model-free augmentation policy for robust image segmentation against natural corruptions.

Findings

Sensitivity analysis runs 10x faster and uses 200x less storage.

Enhanced robustness on real-world and synthetic datasets.

Outperforms existing data augmentation techniques.

Abstract

Achieving robustness in image segmentation models is challenging due to the fine-grained nature of pixel-level classification. These models, which are crucial for many real-time perception applications, particularly struggle when faced with natural corruptions in the wild for autonomous systems. While sensitivity analysis can help us understand how input variables influence model outputs, its application to natural and uncontrollable corruptions in training data is computationally expensive. In this work, we present an adaptive, sensitivity-guided augmentation method to enhance robustness against natural corruptions. Our sensitivity analysis on average runs 10x faster and requires about 200x less storage than previous sensitivity analysis, enabling practical, on-the-fly estimation during training for a model-free augmentation policy. With minimal fine-tuning, our sensitivity-guided augmentation method achieves improved robustness on both real-world and synthetic datasets compared to state-of-the-art data augmentation techniques in image segmentation. Code implementation for this work can be found at: https://github.com/laurayuzheng/SensAug.