20 citations · 39 across the 20 of their papers we have counts for
22 papers
Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation
Amit Aflalo, Shahaf E. Finder, Roy Amoyal +2
Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field exponentially with the numb…
Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment
Roy Amoyal, Oren Freifeld, Chaim Baskin
We present Gaussian Splatting Alignment (GSA), a novel method for aligning two independent 3D Gaussian Splatting (3DGS) models via a similarity transformation (rotation, translatio…
SoftDTW-CUDA-Torch: Memory-Efficient GPU-Accelerated Soft Dynamic Time Warping for PyTorch
Ron Shapira Weber, Oren Freifeld
We present softdtw-cuda-torch, an open-source PyTorch library for computing Soft Dynamic Time Warping (SoftDTW) on GPUs. Our implementation addresses three key limitations of exist…
FastJAM: a Fast Joint Alignment Model for Images
Omri Hirsch, Ron Shapira Weber, Shira Ifergane +1
Joint Alignment (JA) of images aims to align a collection of images into a unified coordinate frame, such that semantically-similar features appear at corresponding spatial locatio…
Synchronization of Multiple Videos
Avihai Naaman, Ron Shapira Weber, Oren Freifeld
Synchronizing videos captured simultaneously from multiple cameras in the same scene is often easy and typically requires only simple time shifts. However, synchronizing videos fro…
Clustering via Self-Supervised Diffusion
Roy Uziel, Irit Chelly, Oren Freifeld +1
Diffusion models, widely recognized for their success in generative tasks, have not yet been applied to clustering. We introduce Clustering via Diffusion (CLUDI), a self-supervised…
TimePoint: Accelerated Time Series Alignment via Self-Supervised Keypoint and Descriptor Learning
Ron Shapira Weber, Shahar Ben Ishay, Andrey Lavrinenko +2
Fast and scalable alignment of time series is a fundamental challenge in many domains. The standard solution, Dynamic Time Warping (DTW), struggles with poor scalability and sensit…
Improving the Effective Receptive Field of Message-Passing Neural Networks
Shahaf E. Finder, Ron Shapira Weber, Moshe Eliasof +2
Message-Passing Neural Networks (MPNNs) have become a cornerstone for processing and analyzing graph-structured data. However, their effectiveness is often hindered by phenomena su…
Consistent Amortized Clustering via Generative Flow Networks
Irit Chelly, Roy Uziel, Oren Freifeld +1
Neural models for amortized probabilistic clustering yield samples of cluster labels given a set-structured input, while avoiding lengthy Markov chain runs and the need for explici…
Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averaging
Ron Shapira Weber, Oren Freifeld
In time-series analysis, nonlinear temporal misalignment remains a pivotal challenge that forestalls even simple averaging. Since its introduction, the Diffeomorphic Temporal Align…
Leveraging Computational Pathology AI for Noninvasive Optical Imaging Analysis Without Retraining
Danny Barash, Emilie Manning, Aidan Van Vleck +10
Noninvasive optical imaging modalities can probe patient's tissue in 3D and over time generate gigabytes of clinically relevant data per sample. There is a need for AI models to an…
Gaussian Splashing: Direct Volumetric Rendering Underwater
Nir Mualem, Roy Amoyal, Oren Freifeld +1
In underwater images, most useful features are occluded by water. The extent of the occlusion depends on imaging geometry and can vary even across a sequence of burst images. As a…
Wavelet Convolutions for Large Receptive Fields
Shahaf E. Finder, Roy Amoyal, Eran Treister +1
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-at…
Trainable Highly-expressive Activation Functions
Irit Chelly, Shahaf E. Finder, Shira Ifergane +1
Nonlinear activation functions are pivotal to the success of deep neural nets, and choosing the appropriate activation function can significantly affect their performance. Most net…
SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images
Nir Barel, Ron Shapira Weber, Nir Mualem +2
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.…
A Deep Moving-camera Background Model
Guy Erez, Ron Shapira Weber, Oren Freifeld
In video analysis, background models have many applications such as background/foreground separation, change detection, anomaly detection, tracking, and more. However, while learni…
CPU- and GPU-based Distributed Sampling in Dirichlet Process Mixtures for Large-scale Analysis
Or Dinari, Raz Zamir, John W. Fisher +1
In the realm of unsupervised learning, Bayesian nonparametric mixture models, exemplified by the Dirichlet Process Mixture Model (DPMM), provide a principled approach for adapting…
DeepDPM: Deep Clustering With an Unknown Number of Clusters
Meitar Ronen, Shahaf E. Finder, Oren Freifeld
Deep Learning (DL) has shown great promise in the unsupervised task of clustering. That said, while in classical (i.e., non-deep) clustering the benefits of the nonparametric appro…
Common Failure Modes of Subcluster-based Sampling in Dirichlet Process Gaussian Mixture Models -- and a Deep-learning Solution
Vlad Winter, Or Dinari, Oren Freifeld
The Dirichlet Process Gaussian Mixture Model (DPGMM) is often used to cluster data when the number of clusters is unknown. One main DPGMM inference paradigm relies on sampling. Her…
Sampling in Dirichlet Process Mixture Models for Clustering Streaming Data
Or Dinari, Oren Freifeld
Practical tools for clustering streaming data must be fast enough to handle the arrival rate of the observations. Typically, they also must adapt on the fly to possible lack of sta…
Effective Learning of a GMRF Mixture Model
Shahaf E. Finder, Eran Treister, Oren Freifeld
Learning a Gaussian Mixture Model (GMM) is hard when the number of parameters is too large given the amount of available data. As a remedy, we propose restricting the GMM to a Gaus…
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
Søren Hauberg, Oren Freifeld, Anders Boesen Lindbo Larsen +2
Data augmentation is a key element in training high-dimensional models. In this approach, one synthesizes new observations by applying pre-specified transformations to the original…