提升U-Net可解释性与不确定性估计，性能更稳参数更少
EU-Nets: Enhanced, Explainable and Parsimonious U-Nets
- 用等效卷积核统一多层卷积，增强模型可读性
- 通过解码器梯度一致性评估不确定性，平均准确率提升1.389%
- 仅需不到0.1万参数，适合资源受限场景
本研究提出MHEX+框架，适用于任意U-Net结构。基于此，我们设计新型U-Net变体EU-Nets，提升可解释性与不确定性估计能力，克服传统U-Net局限，同时改善性能与稳定性。核心创新为等效卷积核，可合并连续卷积层，增强可解释性；在不确定性估计方面，提出协作梯度法，衡量解码器各层梯度一致性。实验表明，EU-Nets在所有网络与数据集上平均准确率提升1.389%，方差降低0.83%，且参数量少于0.1M。
原文摘要 · Abstract (English)
In this study, we propose MHEX+, a framework adaptable to any U-Net architecture. Built upon MHEX+, we introduce novel U-Net variants, EU-Nets, which enhance explainability and uncertainty estimation, addressing the limitations of traditional U-Net models while improving performance and stability. A key innovation is the Equivalent Convolutional Kernel, which unifies consecutive convolutional layers, boosting interpretability. For uncertainty estimation, we propose the collaboration gradient approach, measuring gradient consistency across decoder layers. Notably, EU-Nets achieve an average accuracy improvement of 1.389\% and a variance reduction of 0.83\% across all networks and datasets in our experiments, requiring fewer than 0.1M parameters.
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。