V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models
- URL: http://arxiv.org/abs/2505.05659v1
- Date: Thu, 08 May 2025 21:35:35 GMT
- Title: V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models
- Authors: Guilherme Vieira Neto, Marcos Eduardo Valle,
- Abstract summary: V-EfficientNets is a novel extension of EfficientNet designed to process arbitrary vector-valued data.<n>The proposed models are evaluated on a medical image classification task, achieving an average accuracy of 99.46%.<n>V-EfficientNets demonstrate remarkable efficiency, significantly reducing parameters while outperforming state-of-the-art models.
- Score: 0.4143603294943439
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- VCNet: Recreating High-Level Visual Cortex Principles for Robust Artificial Vision [0.0]
We introduce Visual Cortex Network (VCNet), a novel neural network architecture based on the macro-scale organization of the primate visual cortex.<n> VCNet emulates key biological mechanisms, including hierarchical processing across distinct cortical areas, dual-stream information segregation, and top-down predictive feedback.<n>Our results show that VCNet achieves a classification accuracy of 92.1% on Spots-10 and 74.4% on the light field dataset, surpassing contemporary models of comparable size.
arXiv Detail & Related papers (2025-08-05T01:52:42Z) - Exploring Neural Network Pruning with Screening Methods [3.443622476405787]
Modern deep learning models have tens of millions of parameters which makes the inference processes resource-intensive.<n>This paper proposes and evaluates a network pruning framework that eliminates non-essential parameters.<n>The proposed framework produces competitive lean networks compared to the original networks.
arXiv Detail & Related papers (2025-02-11T02:31:04Z) - A Multi-Fidelity Graph U-Net Model for Accelerated Physics Simulations [1.2430809884830318]
We propose a novel GNN architecture, Multi-Fidelity U-Net, that utilizes the advantages of the multi-fidelity methods for enhancing the performance of the GNN model.<n>We show that the proposed approach performs significantly better in accuracy and data requirement.<n>We also present Multi-Fidelity U-Net Lite, a faster version of the proposed architecture, with 35% faster training, with 2 to 5% reduction in accuracy.
arXiv Detail & Related papers (2024-12-19T20:09:38Z) - Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
We propose to represent neural networks as computational graphs of parameters.
Our approach enables a single model to encode neural computational graphs with diverse architectures.
We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
arXiv Detail & Related papers (2024-03-18T18:01:01Z) - Supervised Training of Siamese Spiking Neural Networks with Earth's
Mover Distance [4.047840018793636]
This study adapts the highly-versatile siamese neural network model to the event data domain.
We introduce a supervised training framework for optimizing Earth's Mover Distance between spike trains with spiking neural networks (SNN)
arXiv Detail & Related papers (2022-02-20T00:27:57Z) - Anomaly Detection on Attributed Networks via Contrastive Self-Supervised
Learning [50.24174211654775]
We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks.
Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair.
A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
arXiv Detail & Related papers (2021-02-27T03:17:20Z) - Encoding the latent posterior of Bayesian Neural Networks for
uncertainty quantification [10.727102755903616]
We aim for efficient deep BNNs amenable to complex computer vision architectures.
We achieve this by leveraging variational autoencoders (VAEs) to learn the interaction and the latent distribution of the parameters at each network layer.
Our approach, Latent-Posterior BNN (LP-BNN), is compatible with the recent BatchEnsemble method, leading to highly efficient (in terms of computation and memory during both training and testing) ensembles.
arXiv Detail & Related papers (2020-12-04T19:50:09Z) - DRU-net: An Efficient Deep Convolutional Neural Network for Medical
Image Segmentation [2.3574651879602215]
Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs)
We propose an efficient network architecture by considering advantages of both networks.
arXiv Detail & Related papers (2020-04-28T12:16:24Z) - Binarized Graph Neural Network [65.20589262811677]
We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters.
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches.
Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
arXiv Detail & Related papers (2020-04-19T09:43:14Z) - Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction.
We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data.
Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
arXiv Detail & Related papers (2020-03-10T03:10:41Z) - Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters.
Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques.
We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
arXiv Detail & Related papers (2020-02-03T04:11:13Z) - Model Fusion via Optimal Transport [64.13185244219353]
We present a layer-wise model fusion algorithm for neural networks.
We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
arXiv Detail & Related papers (2019-10-12T22:07:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.