David S. W. Williams — accepted AI-conference papers

2024

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

David S. W. Williams, Matthew Gadd, Paul Newman, Daniele De Martini

ICRA 2024poster

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-parame…

Cited by 1 Source ↗Scholar ↗

2021

Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning

David S. W. Williams, Matthew Gadd, Daniele De Martini, Paul Newman

ICRA 2021poster

In this work, a neural network is trained to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD dataset with a novel contrastive objective and data…

Cited by 16 Source ↗Scholar ↗