# LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks

Source: [LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks](<https://www.sota2.com/research/paper/68fa65be1e209131cea0c129>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:34:37.515Z

Authors: Jonathan Ephrath, Lars Ruthotto, Eldad Haber, Eran Treister

Published: 2019-04-15T10:28:42.000Z

## Abstract

Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the training of and prediction with CNNs. To improve the efficiency of CNNs, we introduce lean convolution operators that reduce the number of parameters and computational complexity, and can be used in a wide range of existing CNNs. Here, we exemplify their use in residual networks (ResNets), which have been very reliable for a few years now and analyzed intensively. In our experiments on three image classification problems, the proposed LeanResNet yields results that are comparable to other recently proposed reduced architectures using similar number of parameters.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.06952>)

[PDF](<https://arxiv.org/pdf/1904.06952.pdf>)