# Exploring Randomly Wired Neural Networks for Image Recognition

Source: [Exploring Randomly Wired Neural Networks for Image Recognition](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b3fc>)

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

Data updated: 2026-01-04T04:08:44.823Z

Authors: Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He

Published: 2019-04-02T17:57:16.000Z

## Abstract

Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do this, we first define the concept of a stochastic network generator that encapsulates the entire network generation process. Encapsulation provides a unified view of NAS and randomly wired networks. Then, we use three classical random graph models to generate randomly wired graphs for networks. The results are surprising: several variants of these random generators yield network instances that have competitive accuracy on the ImageNet benchmark. These results suggest that new efforts focusing on designing better network generators may lead to new breakthroughs by exploring less constrained search spaces with more room for novel design.

## 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 CIFAR-10 DARTS search space (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-darts-search-space-test.md>): Image Classification; CIFAR-10 DARTS search space (test); Best Test Error: 2.71.

- [Image Classification on ImageNet](<https://www.sota2.com/research/sota/image-classification-on-imagenet.md>): Image Classification; ImageNet; Top-1 Accuracy: 74.7.

- [Image Classification on ImageNet (val)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val.md>): Image Classification; ImageNet (val); Top-1 Acc: 79.

- [Image Classification on ImageNet 1k (val)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val.md>): Image Classification; ImageNet-1k (val); Top-1 Accuracy: 80.1.

- [Object Detection on COCO 2017 (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-2017-val.md>): Object Detection; COCO 2017 (val); AP: 41.1.

- [Image Classification on ImageNet (val) (Top-1 and Top-5 Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-top-1-and-top-5-accuracy.md>): Image Classification; ImageNet (val); Top-1 Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.01569>)

[PDF](<https://arxiv.org/pdf/1904.01569.pdf>)