activity
20162026
most citedIMEXnet: A Forward Stable Deep Neural Network

24 citations · 114 across the 43 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2026

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…

cs.CV2024

Towards Croppable Implicit Neural Representations

Maor Ashkenazi, Eran Treister

Implicit Neural Representations (INRs) have peaked interest in recent years due to their ability to encode natural signals using neural networks. While INRs allow for useful applic…

cs.CV2024★ 12 cited

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…

cs.CV2022

Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks

Moshe Eliasof, Nir Ben Zikri, Eran Treister

Unsupervised image segmentation is an important task in many real-world scenarios where labelled data is of scarce availability. In this paper we propose a novel approach that harn…

cs.CV2022★ 1 cited

Rethinking Unsupervised Neural Superpixel Segmentation

Moshe Eliasof, Nir Ben Zikri, Eran Treister

Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network…

cs.CV2022★ 18 cited

Wavelet Feature Maps Compression for Image-to-Image CNNs

Shahaf E. Finder, Yair Zohav, Maor Ashkenazi +1

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. Whi…