Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Longwei, Li, Xueqian, Zhang, Zheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909422030159872
author Wang, Longwei
Li, Xueqian
Zhang, Zheng
author_facet Wang, Longwei
Li, Xueqian
Zhang, Zheng
contents The resilience of convolutional neural networks against input variations and adversarial attacks remains a significant challenge in image recognition tasks. Motivated by the need for more robust and reliable image recognition systems, we propose the Dense Cross-Connected Ensemble Convolutional Neural Network (DCC-ECNN). This novel architecture integrates the dense connectivity principle of DenseNet with the ensemble learning strategy, incorporating intermediate cross-connections between different DenseNet paths to facilitate extensive feature sharing and integration. The DCC-ECNN architecture leverages DenseNet's efficient parameter usage and depth while benefiting from the robustness of ensemble learning, ensuring a richer and more resilient feature representation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07022
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness
Wang, Longwei
Li, Xueqian
Zhang, Zheng
Computer Vision and Pattern Recognition
Artificial Intelligence
The resilience of convolutional neural networks against input variations and adversarial attacks remains a significant challenge in image recognition tasks. Motivated by the need for more robust and reliable image recognition systems, we propose the Dense Cross-Connected Ensemble Convolutional Neural Network (DCC-ECNN). This novel architecture integrates the dense connectivity principle of DenseNet with the ensemble learning strategy, incorporating intermediate cross-connections between different DenseNet paths to facilitate extensive feature sharing and integration. The DCC-ECNN architecture leverages DenseNet's efficient parameter usage and depth while benefiting from the robustness of ensemble learning, ensuring a richer and more resilient feature representation.
title Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.07022