# Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks

Source: [Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks](<https://www.sota2.com/research/paper/68fa63301e209131ce9fd2fb>)

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

Data updated: 2025-10-28T13:56:33.207Z

Authors: Chen Yunpeng, Jin Xiaojie, Kang Bingyi, Feng Jiashi, Yan Shuicheng

Published: 2017-03-07T02:20:57.000Z

## Abstract

Residual units are wildly used for alleviating optimization difficulties when building deep neural networks. However, the performance gain does not well compensate the model size increase, indicating low parameter efficiency in these residual units. In this work, we first revisit the residual function in several variations of residual units and demonstrate that these residual functions can actually be explained with a unified framework based on generalized block term decomposition. Then, based on the new explanation, we propose a new architecture, Collective Residual Unit (CRU), which enhances the parameter efficiency of deep neural networks through collective tensor factorization. CRU enables knowledge sharing across different residual units using shared factors. Experimental results show that our proposed CRU Network demonstrates outstanding parameter efficiency, achieving comparable classification performance to ResNet-200 with the model size of ResNet-50. By building a deeper network using CRU, we can achieve state-of-the-art single model classification accuracy on ImageNet-1k and Places365-Standard benchmark datasets. (Code and trained models are available on GitHub)

## 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/1703.02180>)

[PDF](<https://arxiv.org/pdf/1703.02180.pdf>)
