5 papers
Platonic Transformers: A Solid Choice For Equivariance
Mohammad Mohaiminul Islam, Rishabh Anand, David R. Wessels +7
While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and…
Longitudinal Flow Matching for Trajectory Modeling
Mohammad Mohaiminul Islam, Thijs P. Kuipers, Sharvaree Vadgama +4
Generative models for sequential data often struggle with sparsely sampled and high-dimensional trajectories, typically reducing the learning of dynamics to pairwise transitions. W…
Probing Equivariance and Symmetry Breaking in Convolutional Networks
Sharvaree Vadgama, Mohammad Mohaiminul Islam, Domas Buracas +3
In this work, we explore the trade-offs of explicit structural priors, particularly group equivariance. We address this through theoretical analysis and a comprehensive empirical s…
Uncertainty-aware retinal layer segmentation in OCT through probabilistic signed distance functions
Mohammad Mohaiminul Islam, Coen de Vente, Bart Liefers +3
In this paper, we present a new approach for uncertainty-aware retinal layer segmentation in Optical Coherence Tomography (OCT) scans using probabilistic signed distance functions…
Conditioning 3D Diffusion Models with 2D Images: Towards Standardized OCT Volumes through En Face-Informed Super-Resolution
Coen de Vente, Mohammad Mohaiminul Islam, Philippe Valmaggia +3
High anisotropy in volumetric medical images can lead to the inconsistent quantification of anatomical and pathological structures. Particularly in optical coherence tomography (OC…