Answers are grounded in this paper and cite their sources.
Evaluates image segmentation corruption due to noise, indicating potential safety risks for autonomous systems.
Image segmentation applications are a core component of safety-critical autonomous software pipelines. Sensor data input noise can lead to segmentation output corruption that threatens safety in both DNN- and transformer-based segmenters. Previous work has proposed methods for generating malicious noise to cause DNN- and transformer-based object detection and classification output corruption. We perform the same task for image segmentation applications using genetic algorithms for optimization. We then propose a novel method to predict whether an input image will yield a corrupted segmentation output due to noise. We evaluate the optimal noise generation and corruption prediction on state-of-the-art image segmenters YOLOv8 and DETR. We observe that we can (a) cause segmentation output corruption with noise that is undetectable to the human eye and unrelated to the corrupted region of the image; and (b) predict output corruption due to image noise with over 96% accuracy.
No takes yet. Share an insight, caveat, or question.
Bozoukov et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: