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

TL;DR

This paper introduces DCC-ECNN, a novel neural network architecture that combines DenseNet's dense connectivity with ensemble learning to improve robustness against input variations and adversarial attacks.

Contribution

The paper presents a new Dense Cross-Connected Ensemble CNN architecture that enhances robustness by integrating dense connectivity and ensemble strategies.

Findings

Improved resilience to input variations and adversarial attacks.

Enhanced feature sharing and integration through cross-connections.

Efficient parameter usage with increased robustness.

Abstract

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.