2.2k citations · 5.8k across the 101 of their papers we have counts for
10 papers · 1 filter
A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classification
Alan Q. Wang, Mert R. Sabuncu
In this paper, we empirically analyze a simple, non-learnable, and nonparametric Nadaraya-Watson (NW) prediction head that can be used with any neural network architecture. In the…
Decoding natural image stimuli from fMRI data with a surface-based convolutional network
Zijin Gu, Keith Jamison, Amy Kuceyeski +1
Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMR…
LARO: Learned Acquisition and Reconstruction Optimization to accelerate Quantitative Susceptibility Mapping
Jinwei Zhang, Pascal Spincemaille, Hang Zhang +6
Quantitative susceptibility mapping (QSM) involves acquisition and reconstruction of a series of images at multi-echo time points to estimate tissue field, which prolongs scan time…
GLACIAL: Granger and Learning-based Causality Analysis for Longitudinal Imaging Studies
Minh Nguyen, Gia H. Ngo, Mert R. Sabuncu
The Granger framework is useful for discovering causal relations in time-varying signals. However, most Granger causality (GC) methods are developed for densely sampled timeseries…
A Transformer-based Neural Language Model that Synthesizes Brain Activation Maps from Free-Form Text Queries
Gia H. Ngo, Minh Nguyen, Nancy F. Chen +1
Neuroimaging studies are often limited by the number of subjects and cognitive processes that can be feasibly interrogated. However, a rapidly growing number of neuroscientific stu…
Semi-Parametric Inducing Point Networks and Neural Processes
Richa Rastogi, Yair Schiff, Alon Hacohen +5
We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner. Semi-pa…
Label conditioned segmentation
Tianyu Ma, Benjamin C. Lee, Mert R. Sabuncu
Semantic segmentation is an important task in computer vision that is often tackled with convolutional neural networks (CNNs). A CNN learns to produce pixel-level predictions throu…
Hyper-Convolutions via Implicit Kernels for Medical Imaging
Tianyu Ma, Alan Q. Wang, Adrian V. Dalca +1
The convolutional neural network (CNN) is one of the most commonly used architectures for computer vision tasks. The key building block of a CNN is the convolutional kernel that ag…
Computing Multiple Image Reconstructions with a Single Hypernetwork
Alan Q. Wang, Adrian V. Dalca, Mert R. Sabuncu
Deep learning based techniques achieve state-of-the-art results in a wide range of image reconstruction tasks like compressed sensing. These methods almost always have hyperparamet…
Personalized visual encoding model construction with small data
Zijin Gu, Keith Jamison, Mert Sabuncu +1
Encoding models that predict brain response patterns to stimuli are one way to capture this relationship between variability in bottom-up neural systems and individual's behavior o…