GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection
Xiang Li, Wenxi Li, Yuetong Wang, Chenyang Lyu, Haozhe Lin, Guiguang Ding, Yuchen Guo
Abstract
Object detection in High-Resolution Wide (HRW) shots, or gigapixel images, presents unique challenges due to extreme object sparsity and vast scale variations. State-of-the-art methods like SparseFormer have pioneered sparse processing by selectively focusing on important regions, yet they apply a uniform computational model to all selected regions, overlooking their intrinsic complexity differences. This leads to a suboptimal trade-off between performance and efficiency. In this paper, we introduce GigaMoE, a novel backbone architecture that pioneers adaptive computation for this domain by replacing the standard Feed-Forward Networks (FFNs) with a Mixture-of-Experts (MoE) module. Our architecture first employs a shared expert to provide a robust feature baseline for all selected regions. Upon this foundation, our core innovation---a novel Sparsity-Guided Routing mechanism---insightfully repurposes importance scores from the sparse backbone to provide a "computational bonus,
BibTeX
@inproceedings{aaai2026_gigamoesparsityg,
title = {GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection},
author = {Xiang Li and Wenxi Li and Yuetong Wang and Chenyang Lyu and Haozhe Lin and Guiguang Ding and Yuchen Guo},
booktitle = {AAAI 2026},
year = {2026}
}