EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Layer-wise Rank Allocation for Parameter-Efficient Fine-Tuning in Vision Transformers

Qiuyu Chen

ITM Web of Conferences · 2026 · 89 · 01005

DOI: 10.1051/itmconf/20268901005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ITM Web of Conferences, online erschienen am 14.08.2026. Verfasst von Qiuyu Chen. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision Transformer (ViT) obtains state-of-the-art performance but is expensive to fine-tune because of the large number of parameters. Parameter-efficient tuning methods, such as LoRA, have been proposed. However, existing methods tend to ignore the hierarchical structure of representation learning and assume the same distributed-rank assignment for all layers. This paper offers a rank assignment technique for LoRA finetuning of Vision Transformer with layer-wise differential ranking rather than uniform, which gives better channel utilization efficiency. The test used the CIFAR-100 dataset with the ViT Tiny model. The testing results show that the method can achieve 0.8086 average accuracy while decreasing the tunable parameter ratio to 2.43% from the original 4.09%, which is an advantage over LoRA with its uniform rank. Additionally, the method is seed-agnostic, and thus, the approach is reasonably stable. These findings suggest that placing different hierarchies increases parameter efficiency; hence, it is a viable method that can be used to efficiently fine-tune Vision Transformers.

Zitieren

APA

Chen, Q. (2026). Layer-wise Rank Allocation for Parameter-Efficient Fine-Tuning in Vision Transformers. ITM Web of Conferences, 89, 01005. https://doi.org/10.1051/itmconf/20268901005

Vancouver

Chen Q. Layer-wise Rank Allocation for Parameter-Efficient Fine-Tuning in Vision Transformers. ITM Web of Conferences. 2026;89:01005. doi:10.1051/itmconf/20268901005

BibTeX
@article{Chen2026,
  author = {Chen, Qiuyu},
  title = {Layer-wise Rank Allocation for Parameter-Efficient Fine-Tuning in Vision Transformers},
  journal = {ITM Web of Conferences},
  year = {2026},
  volume = {89},
  pages = {01005},
  doi = {10.1051/itmconf/20268901005}
}
Kostenlos starten →