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

EasyChair Preprint no. 13733

Abstract

The resilience of Convolutional Neural Networks (CNNs) 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.

Keyphrases: Cross-Connected, Dense Deep Neural Networks, ensemble learning strategy, generalization, robustness

@Booklet{EasyChair:13733,
  author = {Longwei Wang},
  title = {Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness},
  howpublished = {EasyChair Preprint no. 13733},

  year = {EasyChair, 2024}}