# Efficient Scale-Permuted Backbone with Learned Resource Distribution

arXiv: https://arxiv.org/abs/2010.11426 · HTML: https://mlsanity.com/paper/2010.11426/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [Simple Training Strategies and Model Scaling for Object Detection](https://mlsanity.com/paper/2107.00057/) (2021)
- [Dilated SpineNet for Semantic Segmentation](https://mlsanity.com/paper/2103.12270/) (2021)
- [Optimizing Anchor-based Detectors for Autonomous Driving Scenes](https://mlsanity.com/paper/2208.06062/) (2022)

## Abstract (arXiv)

Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combining scale-permuted backbone with advanced efficient operations and compound scaling. Furthermore, SpineNet is built with a uniform resource distribution over operations. While this strategy seems to be prevalent for scale-decreased models, it may not be an optimal design for scale-permuted models. In this work, we propose a simple technique to combine efficient operations and compound scaling with a previously learned scale-permuted architecture. We demonstrate the efficiency of scale-permuted model can be further improved by learning a resource distribution over the entire network. The resulting efficient scale-permuted models outperform state-of-the-art EfficientNet-based models on object detection and achieve competitive performance on image classification and semantic segmentation. Code and models will be open-sourced soon.