4 papers
Towards Integrating Uncertainty for Domain-Agnostic Segmentation
Jesse Brouwers, Xiaoyan Xing, Alexander Timans
Foundation models for segmentation such as the Segment Anything Model (SAM) family exhibit strong zero-shot performance, but remain vulnerable in shifted or limited-knowledge domai…
On Equivariant Model Selection through the Lens of Uncertainty
Putri A. van der Linden, Alexander Timans, Dharmesh Tailor +1
Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored…
On Continuous Monitoring of Risk Violations under Unknown Shift
Alexander Timans, Rajeev Verma, Eric Nalisnick +1
Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assur…
CP: Leveraging Geometry for Conformal Prediction via Canonicalization
Putri A. van der Linden, Alexander Timans, Erik J. Bekkers
We study the problem of conformal prediction (CP) under geometric data shifts, where data samples are susceptible to transformations such as rotations or flips. While CP endows pre…