V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models

2025/05/08 by Guilherme Vieira Neto, Neto, Guilherme Vieira, Marcos Eduardo Valle +1
Computer Science · #AI in cancer detection #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.05659

openalex publication_date 2025/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

EfficientNet models are convolutional neural networks optimized for parameter allocation by jointly balancing network width, depth, and resolution. Renowned for their exceptional accuracy, these models have become a standard for image classification tasks across diverse computer vision benchmarks. While traditional neural networks learn correlations between feature channels during training, vector-valued neural networks inherently treat multidimensional data as coherent entities, taking for granted the inter-channel relationships. This paper introduces vector-valued EfficientNets (V-EfficientNets), a novel extension of EfficientNet designed to process arbitrary vector-valued data. The proposed models are evaluated on a medical image classification task, achieving an average accuracy of 99.46% on the ALL-IDB2 dataset for detecting acute lymphoblastic leukemia. V-EfficientNets demonstrate remarkable efficiency, significantly reducing parameters while outperforming state-of-the-art models, including the original EfficientNet. The source code is available at https://github.com/mevalle/v-nets.

Citations

• Novel computational workflows for natural and biomedical image processing based on hypercomplex algebras
• Quaternion Neural Networks: A physics-incorporated intelligence framework
• Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks
• Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling
• EfficientNetV2: Smaller Models and Faster Training
• Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• Fundamental tenis : resep meraih kemenangan / Tony Mottram
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Backpropagation with N-D Vector-Valued Neurons Using Arbitrary Bilinear Products
• Squeeze-and-Excitation Networks
• Deep Residual Learning for Image Recognition

Related

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• ImageNet classification with deep convolutional neural networks
• Convolutional Neural Networks:
• Do deep neural networks utilize the weight space efficiently?
• CVNets: High Performance Library for Computer Vision