Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness
This addresses the need for more robust and reliable image recognition systems, but appears incremental as it combines existing methods like DenseNet and ensemble learning.
The paper tackled the problem of improving the robustness of convolutional neural networks against input variations and adversarial attacks in image recognition by proposing the Dense Cross-Connected Ensemble Convolutional Neural Network (DCC-ECNN), which integrates dense connectivity and ensemble learning with cross-connections, but no concrete results or numbers are provided in the 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.