Papers › Data-Driven Neuron Allocation for Scale Aggregation Networks
Data-Driven Neuron Allocation for Scale Aggregation Networks
Yi Li, Zhanghui Kuang, Yimin Chen, Wayne Zhang
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | ImageNet | ScaleNet-152 | GFLOPs | 11.2 | #763 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ScaleNet-152 | Top 1 Accuracy | 79.38% | #763 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ScaleNet-101 | GFLOPs | 7.5 | #787 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ScaleNet-101 | Top 1 Accuracy | 79.03% | #787 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ScaleNet-50 | GFLOPs | 3.8 | #863 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ScaleNet-50 | Top 1 Accuracy | 77.8% | #863 of 1060 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: Scale Aggregation Block, ScaleNet
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections