Learning to Generate Training Datasets for Robust Semantic Segmentation

arXiv:2308.02535v4 Announce Type: replace-cross
Abstract: Semantic segmentation methods have advanced significantly. Still, their robustness to real-world perturbations and object types not seen during training remains a challenge, particularly in safety-critical applications. We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models. Specifically, we design Robusta, a novel robust conditional generative adversarial network to generate realistic and plausible perturbed images that can be used to train reliable …

arxiv cs.cv cs.lg datasets generate robust segmentation semantic training training datasets type