Rudrasis Chakraborty's research while affiliated with University of California, Berkeley and other places

Publications (20)

Preprint
Full-text available
Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outcomes) that may otherwise be too weak to detect. When there is only a {\em single} source of variability (e.g., different scanners), domain adaptation and matching the dis...
Preprint
Full-text available
Panel data involving longitudinal measurements of the same set of participants taken over multiple time points is common in studies to understand childhood development and disease modeling. Deep hybrid models that marry the predictive power of neural networks with physical simulators such as differential equations, are starting to drive advances in...
Preprint
Full-text available
Generative models which use explicit density modeling (e.g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e.g. Gaussian, to the unknown input distribution. This often requires searching over a class of non-linear functions (e.g., representable by a deep neural network). While effective...
Article
Dominantly inherited Alzheimer’s disease (DIAD) and late onset Alzheimer’s disease (LOAD) are characterized by the accumulation of amyloid pathology, and neurodegeneration which heralds the onset of dementia. Loss of structural connectivity prior to development of dementia may be measured using techniques that are sensitive to subtle neurodegenerat...
Article
Significance: Quantifying meibomian gland morphology from meibography images is used for the diagnosis, treatment, and management of meibomian gland dysfunction in clinics. A novel and automated method is described for quantifying meibomian gland morphology from meibography images. Purpose: Meibomian gland morphological abnormality is a common c...
Article
Panel data involving longitudinal measurements of the same set of participants taken over multiple time points is common in studies to understand childhood development and disease modeling. Deep hybrid models that marry the predictive power of neural networks with physical simulators such as differential equations, are starting to drive advances in...
Article
Deep neural networks can efficiently process 3D point clouds. At each point convolution layer, local features can be learned from local neighborhoods of point clouds. These features are combined together for further processing to extract the semantic information encoded in the point cloud. Previous networks adopt all the same local neighborhoods at...
Article
Complex-valued data are ubiquitous in signal and image processing applications, and complex-valued representations in deep learning have appealing theoretical properties. While these aspects have long been recognized, complex-valued deep learning continues to lag far behind its real-valued counterpart. We propose a principled geometric approach to...
Preprint
The James-Stein (JS) shrinkage estimator is a biased estimator that captures the mean of Gaussian random vectors.While it has a desirable statistical property of dominance over the maximum likelihood estimator (MLE) in terms of mean squared error (MSE), not much progress has been made on extending the estimator onto manifold-valued data. We propose...
Conference Paper
Full-text available
Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop an efficient approach to impose filter orthogonality on a convolutional layer based on the doubly block-Toeplitz matrix represent...
Article
Full-text available
Purpose: To develop a deep learning approach to digitally segmenting meibomian gland atrophy area and computing percent atrophy in meibography images. Methods: A total of 706 meibography images with corresponding meiboscores were collected and annotated for each one with eyelid and atrophy regions. The dataset was then divided into the developme...
Preprint
Full-text available
The instability and feature redundancy in CNNs hinders further performance improvement. Using orthogonality as a regularizer has shown success in alleviating these issues. Previous works however only considered the kernel orthogonality in the convolution layers of CNNs, which is a necessary but not sufficient condition for orthogonal convolutions i...
Preprint
Point-cloud is an efficient way to represent 3D world. Analysis of point-cloud deals with understanding the underlying 3D geometric structure. But due to the lack of smooth topology, and hence the lack of neighborhood structure, standard correlation can not be directly applied on point-cloud. One of the popular approaches to do point correlation is...
Preprint
Complex-valued deep learning has attracted increasing attention in recent years, due to its versatility and ability to capture more information. However, the lack of well-defined complex-valued operations remains a bottleneck for further advancement. In this work, we propose a geometric way to define deep neural networks on the space of complex num...
Preprint
Point cloud is an efficient representation of 3D visual data, and enables deep neural networks to effectively understand and model the 3D visual world. All the previous methods used the same original point cloud location at different layers of the network to define "local patches". Depending on the neighborhood of the local patches, they learn the...
Preprint
We develop a novel deep learning architecture for naturally complex-valued data, which is often subject to complex scaling ambiguity. We treat each sample as a field in the space of complex numbers. With the polar form of a complex-valued number, the general group that acts in this space is the product of planar rotation and non-zero scaling. This...

Citations

... A major impediment to detailed morphological analysis of meibography images and to its use in both research and clinical eyecare has been the technical difficulty and time-consuming nature of quantifying local meibography features 19 . In a previous work we developed a deep learning model that proved capable of quickly and automatically identifying and quantifying eight different metrics describing both global and local morphological features in novel meibography images with good accuracy 20 . In this study we will build on this work by training a supervised machine learning model to identify and quantify the morphological features observed in de-identified meibography images and then use these images and imagederived metrics to predict the demographic characteristics of the subjects who provided them. ...
... It has achieved promising results in most 2D vision tasks [22,23,43] and in 3D object detection [24,25]. As for 3D semantic segmentation, some works [44][45][46][47] applied the point-based transformer to point clouds for indoor scene semantic segmentation. However, these methods cannot be used for outdoor LiDAR segmentation due to the inherent properties of LiDAR points (e.g., sparsity and varying density). ...
... The cross-terms allow information to flow between the real and imaginary part. This is also the approach taken by SurReal [37] which model complex as a product manifold of scaling and planar rotations. Complex scaling naturally becomes a group of transitive actions. ...
... As Xie et al. (2017); Balestriero et al. (2018); Wang et al. (2020) reveal, imposing orthogonality on kernels leads to better training performance. This motivates us to initiate the training with a set of orthogonal kernels. ...
... Complex-valued networks originated in application domains where the input is complex-valued such as remote sensing [2], [54] and MRI fingerprinting [50]. Compared to standard real-valued networks, complex-valued networks offer three key distinctive advantages for iris recognition that can not be directly achieved by their standard realvalued counterparts. ...
... However, near the transition limits of different levels ( µ − σ and µ + σ ), the morphological features may be very similar and difficult to classify. A similar technique described in Wang et al. 30 was applied here. A tolerance threshold near the grading transition limit was necessary. ...