# Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models

Source: [Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models](<https://www.sota2.com/research/paper/6a13d7a36f71c5ae7dc9e9ec>)

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

Data updated: 2026-05-26T05:00:13.075Z

Authors: Maxim Henry, Adrien Deli\\\`ege, S\\'ebastien Pi\\'erard, Marc Van Droogenbroeck

Published: 2026-05-22T14:08:22.000Z

## Abstract

Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often assume the availability of narrower models, obscuring the true computational cost of the entire pipeline. We propose an efficient training protocol, RBDC, that builds wide models by coupling in a parameter-free block-diagonal way narrower, independently trained models in a recursive way. This allows a flexible allocation of the training budget available across all the models involved. Evaluated with vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, our RBDC training protocol shows a much better efficiency than models trained from scratch with the standard protocol, yielding 30% FLOPs reduction at similar test accuracies. It also achieves higher performances at same training FLOPs than training protocols from the model growth literature. Finally, we show that our models can serve as better backbones than their original counterparts for downstream object detection and instance segmentation tasks.

## 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.

- [Image Classification on ImageNet-1K 1.0 (test) (Top-1 Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-1-0-test-top-1-accuracy.md>): Image Classification; ImageNet-1k 1.0 (test); Top-1 Accuracy: 77.55.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.23656>)

[PDF](<https://arxiv.org/pdf/2605.23656.pdf>)