# Online Convolutional Re-parameterization

Source: [Online Convolutional Re-parameterization](<https://www.sota2.com/research/paper/68fa6c351e209131cea32d10>)

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

Data updated: 2025-10-26T00:06:48.603Z

Authors: Mu Hu, Junyi Feng, Jiashen Hua, Baisheng Lai, Jianqiang Huang, Xiaojin Gong, Xiansheng Hua

Published: 2022-04-02T09:50:19.000Z

## Abstract

Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inference-time cost. Though efficient during inference, such models rely heavily on the complicated training-time blocks to achieve high accuracy, leading to large extra training cost. In this paper, we present online convolutional re-parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. To achieve this goal, we introduce a linear scaling layer for better optimizing the online blocks. Assisted with the reduced training cost, we also explore some more effective re-param components. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. Meanwhile, equipped with OREPA, the models outperform previous methods on ImageNet by up to +0.6%.We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks. Codes are available at https://github.com/JUGGHM/OREPA\_CVPR2022 .

## 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/2204.00826>)

[PDF](<https://arxiv.org/pdf/2204.00826.pdf>)
