4 papers
Segment Anything with Robust Uncertainty-Accuracy Correlation
Hongyou Zhou, Marc Toussaint, Ling Shao +1
Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask score fails to reflect pixel-…
Manifold Sampling via Entropy Maximization
Cornelius V. Braun, Tilman Burghoff, Marc Toussaint
Sampling from constrained distributions has a wide range of applications, including in Bayesian optimization and robotics. Prior work establishes convergence and feasibility guaran…
Amortized Safe Active Learning for Real-Time Data Acquisition: Pretrained Neural Policies From Simulated Nonparametric Functions
Cen-You Li, Marc Toussaint, Barbara Rakitsch +1
Safe active learning (AL) is a sequential scheme for learning unknown systems while respecting safety constraints during data acquisition. Existing methods often rely on Gaussian p…
Amortized Active Learning for Nonparametric Functions
Cen-You Li, Marc Toussaint, Barbara Rakitsch +1
Active learning (AL) is a sequential learning scheme aiming to select the most informative data. AL reduces data consumption and avoids the cost of labeling large amounts of data.…