A Computationally Efficient Multidimensional Vision Transformer

📅 2026-02-23
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the high computational and memory overhead of Vision Transformers in deployment by introducing, for the first time, the tensor cosine product (C-product) into the Vision Transformer architecture. Leveraging the multilinear structure inherent in images and the orthogonality of the cosine transform, the proposed method constructs an efficient attention mechanism and structured feature representation. It achieves competitive accuracy while reducing the number of parameters to 1/C of the original model, where C denotes the number of channels, thereby substantially lowering model complexity. By integrating multilinear algebra with orthogonal transforms, this approach makes notable contributions both theoretically and in terms of practical deployment efficiency.

Technology Category

Application Category

📝 Abstract
Vision Transformers have achieved state-of-the-art performance in a wide range of computer vision tasks, but their practical deployment is limited by high computational and memory costs. In this paper, we introduce a novel tensor-based framework for Vision Transformers built upon the Tensor Cosine Product (Cproduct). By exploiting multilinear structures inherent in image data and the orthogonality of cosine transforms, the proposed approach enables efficient attention mechanisms and structured feature representations. We develop the theoretical foundations of the tensor cosine product, analyze its algebraic properties, and integrate it into a new Cproduct-based Vision Transformer architecture (TCP-ViT). Numerical experiments on standard classification and segmentation benchmarks demonstrate that the proposed method achieves a uniform 1/C parameter reduction (where C is the number of channels) while maintaining competitive accuracy.
Problem

Research questions and friction points this paper is trying to address.

Vision Transformers
computational cost
memory cost
efficient attention
parameter reduction
Innovation

Methods, ideas, or system contributions that make the work stand out.

Tensor Cosine Product
Vision Transformer
Multilinear Structure
Parameter Reduction
Efficient Attention
🔎 Similar Papers
No similar papers found.
A
Alaa El Ichi
Université du Littoral Côte d'Opale, LMPA, 50 rue F. Buisson, 62228 Calais-Cedex, France
K
Khalide Jbilou
Université du Littoral Côte d'Opale, LMPA, 50 rue F. Buisson, 62228 Calais-Cedex, France