Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling

arXiv:2402.17622v1 Announce Type: new
Abstract: This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass. We exploit general representations from foundation models and unlabelled datasets through a Masked Image Modeling (MIM) approach, which is robust to augmentation hyper-parameters and simpler than previous techniques. For neural networks used in safety-critical applications, bias in the training data can lead to errors; therefore it is crucial to understand a network's limitations at run time and act …

abstract arxiv augmentation cs.cv cs.ro datasets exploit foundation general image modeling network parameters quality robust segmentation semantic ssl through type uncertainty via work