# Data-Driven Neuron Allocation for Scale Aggregation Networks

Source: [Data-Driven Neuron Allocation for Scale Aggregation Networks](<https://www.sota2.com/research/paper/68fa65a81e209131cea0bb21>)

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

Data updated: 2026-01-04T03:06:48.739Z

Authors: Yi Li, Zhanghui Kuang, Yimin Chen, Wayne Zhang

Published: 2019-04-20T15:18:20.000Z

## Abstract

Successful visual recognition networks benefit from aggregating information spanning from a wide range of scales. Previous research has investigated information fusion of connected layers or multiple branches in a block, seeking to strengthen the power of multi-scale representations. Despite their great successes, existing practices often allocate the neurons for each scale manually, and keep the same ratio in all aggregation blocks of an entire network, rendering suboptimal performance. In this paper, we propose to learn the neuron allocation for aggregating multi-scale information in different building blocks of a deep network. The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated. Our scale aggregation network (ScaleNet) is constructed by repeating a scale aggregation (SA) block that concatenates feature maps at a wide range of scales. Feature maps for each scale are generated by a stack of downsampling, convolution and upsampling operations. The data-driven neuron allocation and SA block achieve strong representational power at the cost of considerably low computational complexity. The proposed ScaleNet, by replacing all 3x3 convolutions in ResNet with our SA blocks, achieves better performance than ResNet and its outstanding variants like ResNeXt and SE-ResNet, in the same computational complexity. On ImageNet classification, ScaleNets absolutely reduce the top-1 error rate of ResNets by 1.12 (101 layers) and 1.82 (50 layers). On COCO object detection, ScaleNets absolutely improve the mmAP with backbone of ResNets by 3.6 (101 layers) and 4.6 (50 layers) on Faster RCNN, respectively. Code and models are released at https://github.com/Eli-YiLi/ScaleNet.

## 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](<https://www.sota2.com/research/sota/image-classification-on-imagenet.md>): Image Classification; ImageNet; Top-1 Accuracy: 0.98.

- [Object Detection on COCO (val)](<https://www.sota2.com/research/sota/object-detection-on-coco-val.md>): Object Detection; COCO (val); mAP: 37.3.

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

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.09460>)

[PDF](<https://arxiv.org/pdf/1904.09460.pdf>)

[Implementation](<https://github.com/Eli-YiLi/ScaleNet>)
