Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
Abstract
Modern methods for fine-tuning a Vision Transformer (ViT) like Low-Rank Adaptation (LoRA) and its variants demonstrate impressive performance. However, these methods ignore the high-dimensional nature of Multi-Head Attention (MHA) weight tensors. To address this limitation, we propose Canonical Rank Adaptation (CaRA). CaRA leverages tensor mathematics, first by tensorising the transformer into two different tensors; one for projection layers in MHA and the other for feed-forward layers. Second, the tensorised formulation is fine-tuned using the low-rank adaptation in Canonical-Polyadic Decomposition (CPD) form. Employing CaRA efficiently minimizes the number of trainable parameters. Experimentally, CaRA outperforms existing Parameter-Efficient Fine-Tuning (PEFT) methods in visual classification benchmarks such as Visual Task Adaptation Benchmark (VTAB)-1k and Fine-Grained Visual Categorization (FGVC).
Cite
Text
Veeramacheneni et al. "Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Veeramacheneni et al. "Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/veeramacheneni2025icml-canonical/)BibTeX
@inproceedings{veeramacheneni2025icml-canonical,
title = {{Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers}},
author = {Veeramacheneni, Lokesh and Wolter, Moritz and Kuehne, Hilde and Gall, Juergen},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {61108-61125},
volume = {267},
url = {https://mlanthology.org/icml/2025/veeramacheneni2025icml-canonical/}
}