Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers
Lokesh Veeramacheneni, Moritz Wolter, Hilde Kuehne, Juergen Gall
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).
BibTeX
@inproceedings{
veeramacheneni2025canonical,
title={Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers},
author={Lokesh Veeramacheneni and Moritz Wolter and Hilde Kuehne and Juergen Gall},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=vexHifrbJg}
}