Conditional neural fields represent signals continuously, but their effectiveness depends on how the conditional latent representations are inferred from observed data. In meta-learning, this encoding occurs through gradient updates induced by the decoder, tying representation learning directly to decoder design. We fo...
R. L. M. van Herten, Soufiane Ben Haddou, Rachit Saluja et al.· 0 citations
Persistent homology (PH) is a frequently used tool for extracting and preserving topological information from image data, particularly in image segmentation, where preservation of topological structures is important. However, despite its general applicability across dimensionality, domains, and target structures, the r...
Alexander H. Berger, Marco Fontana, Daniel Rueckert et al.· 0 citations
GeoPose is proposed, a population-trained framework that estimates the C-arm pose in a learned canonical frame and transfers it to the native frame of an unseen CTA through projection-space calibration and transform composition, and provides rapid native-frame registration with fixed population-level weights and the ge...
R. L. M. van Herten, Robert Graf, Paula Feldman et al.· 0 citations
MELD (Multi-Task Equilibrated Learning Detector), which instead trains on class-balanced, family-specific AI-versus-human tasks while sharing a common representation of human writing, and its prediction scores remain stable through 2022 and increase from 2023 onward, coinciding with the widespread adoption of LLM-based...
This work introduces a 3D foundation model for LSM data, pretrained on a large curated collection of 3D images spanning multiple organisms, stains, and imaging protocols, and learns transferable volumetric representations by jointly optimizing for masked reconstruction and image-text alignment.
Adina Scheinfeld, Hao-Tan Zhang, Shang Mu et al.· arXiv.org· 1 citation
RegAL is proposed, a unified active semi-supervised framework governed by a shared topology-aware Pareto optimization that couples sample acquisition with unlabeled data utilization and consistently outperforms state-of-the-art AL, SSL, and active semi-supervised baselines across Dice and boundary-distance metrics unde...
Bahram Jafrasteh, Cheng Wan, Heejong Kim et al.· arXiv.org· 0 citations
This paper proposes a novel approach that approximates the resulting joint uncertainty using a low-rank plus diagonal covariance structure, capturing essential output correlations while avoiding the computational burdens of full covariance matrices.
Leonhard F. Feiner, M. Nickel, M. Menten et al.· Trans. Mach. Learn. Res.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
