Metraipolis › archive › dc_571ead0d4122
StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning — arXiv:2608.04811
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04811
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:48:10.306Z
- SHA-256 of the archived text
4d4b3bb3a23a2cbfaa7402d1b505dccb85da926ec72594ef20f33400440dba41- Stable URL of this page
https://metraipolis.com/documento/dc_571ead0d4122
How to cite
StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning — arXiv:2608.04811 — arXiv (en), https://arxiv.org/abs/2608.04811 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_571ead0d4122 (Metraipolis archive dc_571ead0d4122, sha256 4d4b3bb3a23a2cbfaa7402d1b505dccb85da926ec72594ef20f33400440dba41)
BibTeX
@misc{dc571ead0d4122,
title = {StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning — arXiv:2608.04811},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04811},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_571ead0d4122; sha256 4d4b3bb3a23a2cbfaa7402d1b505dccb85da926ec72594ef20f33400440dba41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04811. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Structured pruning enhances the efficiency of deep neural networks (DNNs) by eliminating groups of parameters during inference. Previous methods mostly reduce computational complexity (FLOPs), while semantic segmentation performance (mIoU) slightly drops. Accordingly, recent dynamic structured pruning methods aim at reducing the performance drop, while lowering the FLOPs even more. However, on the ADE20K and Cityscapes benchmarks, our study reveals that on a GPU platform such dynamic methods exhibit a surprisingly low frame rate far below a simple static approach, while having comparable results in mIoU and FLOPs. To address this issue, we propose a static structured pruning method for attention layers, that achieves both, a lower FLOPs and a high frame rate [fps] of the SegFormer network, the latter increased by up to 34% relative on the Cityscapes dataset, while having no mIoU performance drop at all. Our so-called StaticSegFormer method is strongest for small encoders and large images. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.04811 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:37:40.718Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).