Search Results for author:
Found 19 papers, 11 papers with code
Gaussian Splashing: Direct Volumetric Rendering Underwater
Here, we present a new method that takes only a few minutes for reconstruction and renders novel underwater scenes at 140 FPS.
Leveraging Computational Pathology AI for Noninvasive Optical Imaging Analysis Without Retraining
This is achieved without the need for model retraining or fine-tuning.
SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images
The unsupervised task of Joint Alignment (JA) of images is beset by challenges such as high complexity, geometric distortions, and convergence to poor local or even global optima.
Trainable Highly-expressive Activation Functions
Nonlinear activation functions are pivotal to the success of deep neural nets, and choosing the appropriate activation function can significantly affect their performance.
Wavelet Convolutions for Large Receptive Fields
In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks.
A Deep Moving-camera Background Model
Moreover, existing MCBMs usually model the background either on the domain of a typically-large panoramic image or in an online fashion.
CPU- and GPU-based Distributed Sampling in Dirichlet Process Mixtures for Large-scale Analysis
While Chang and Fisher III's implementation (written in MATLAB/C++) used only CPU and was designed for a single multi-core machine, the packages we proposed here distribute the computations efficiently across either multiple multi-core machines or across mutiple GPU streams.
DeepDPM: Deep Clustering With an Unknown Number of Clusters
Using a split/merge framework, a dynamic architecture that adapts to the changing K, and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones).
Ranked #9 on
Unsupervised Image Classification
on ImageNet
Common Failure Modes of Subcluster-based Sampling in Dirichlet Process Gaussian Mixture Models -- and a Deep-learning Solution
We show that the random initialization is often problematic and hurts the otherwise-effective sampler.
Sampling in Dirichlet Process Mixture Models for Clustering Streaming Data
Practical tools for clustering streaming data must be fast enough to handle the arrival rate of the observations.
Effective Learning of a GMRF Mixture Model
However, we show that even for a single Gaussian, when GLASSO is tuned to successfully estimate the sparsity pattern, it does so at the price of a substantial bias of the values of the nonzero entries of the matrix, and we show that this problem only worsens in a mixture setting.
Diffeomorphic Temporal Alignment Nets
In a single-class case, the method is unsupervised: the ground-truth alignments are unknown.
Deep Diffeomorphic Transformer Networks
Spatial Transformer layers allow neural networks, at least in principle, to be invariant to large spatial transformations in image data.
Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It Simple
We propose novel finite-dimensional spaces of R - R transformations, n [?]
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
We then learn a class-specific probabilistic generative models of the transformations in a Riemannian submanifold of the Lie group of diffeomorphisms.
A Mixture of Manhattan Frames: Beyond the Manhattan World
Traditional approaches to scene representation exploit this phenomenon via the somewhat restrictive assumption that every plane is perpendicular to one of the axes of a single coordinate system.
Aerial Reconstructions via Probabilistic Data Fusion
We propose an integrated probabilistic model for multi-modal fusion of aerial imagery, LiDAR data, and (optional) GPS measurements.
Model Transport: Towards Scalable Transfer Learning on Manifolds
We demonstrate the approach by transferring PCA and logistic-regression models of real-world data involving 3D shapes and image descriptors.
A Geometric take on Metric Learning
We then show that this structure gives us a principled way to perform dimensionality reduction and regression according to the learned metrics.
