Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation
This work addresses robustness challenges for image segmentation in real-time perception applications like autonomous systems, offering an incremental improvement over existing data augmentation methods.
The paper tackles the problem of improving robustness in image segmentation models against natural corruptions by introducing an adaptive, sensitivity-guided augmentation method, achieving improved robustness on real-world and synthetic datasets compared to state-of-the-art techniques with a sensitivity analysis that runs 10x faster and uses 200x less storage.
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.