通过密集跨连接增强模型鲁棒性，提升图像识别抗干扰能力。
Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness
- 引入密集跨连接，实现多路径特征深度融合
- 在多个数据集上显著提升对抗样本防御能力
- 适合需要高可靠性的图像识别应用场景
卷积神经网络在面对输入变化和对抗攻击时的鲁棒性仍是图像识别任务中的重大挑战。为构建更稳健可靠的图像识别系统，本文提出密集跨连接集成卷积神经网络（DCC-ECNN）。该架构融合DenseNet的密集连接机制与集成学习策略，在不同DenseNet路径间引入中间跨连接，促进广泛特征共享与融合。DCC-ECNN充分利用DenseNet的高效参数使用与深层结构优势，同时获得集成学习带来的鲁棒性，确保更丰富、更稳健的特征表示。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。