Existing defocus blur detection (DBD) methods usually explore multi-scale and multi-level features to improve performance. However, defocus blur regions normally have incomplete semantic information, which will reduce DBD’s performance if it can’t be used properly. In this paper, we address the above problem by exploring deep ensemble networks, where we boost diversity of defocus blur detectors to force the network to generate diverse results that some rely more on high-level semantic information while some ones rely more on low-level information. Then, diverse result ensemble makes detection errors cancel out each other. Specifically, we propose two deep ensemble networks ( e.g. , adaptive ensemble network (AENet) and encoder-feature ensemble network (EFENet)), which focus on boosting diversity while costing less computation. AENet constructs different light-weight sequential adapters for one backbone network to generate diverse results without introducing too many parameters and computation. AENet is optimized only by the self- negative correlation loss. On the other hand, we propose EFENet by exploring the diversity of multiple encoded features and ensemble strategies of features ( e.g. , group-channel uniformly weighted average ensemble and self-gate weighted ensemble). Diversity is represented by encoded features with less parameters, and a simple mean squared error loss can achieve the superior performance. Experimental results demonstrate the superiority over the state-of-the-arts in terms of accuracy and speed. Codes and models are available at: https://github.com/wdzhao123/DENets .

中文翻译：

---

通过提高深度集成网络的多样性进行散焦模糊检测

现有的散焦模糊检测 (DBD) 方法通常探索多尺度和多级特征以提高性能。然而，散焦模糊区域通常具有不完整的语义信息，如果不能正确使用会降低DBD的性能。在本文中，我们通过探索深度集成网络来解决上述问题，其中我们提高了散焦模糊检测器的多样性，以迫使网络生成不同的结果，有些更依赖于高级语义信息，而有些则更依赖于低级语义信息。信息。然后，不同的结果集成使检测错误相互抵消。具体来说，我们提出了两个深度集成网络（ 例如 、自适应集成网络 (AENet) 和编码器特征集成网络 (EFENet)，它们专注于提高多样性，同时减少计算成本。AENet 为一个主干网络构建不同的轻量级顺序适配器，以生成不同的结果，而不会引入太多的参数和计算。AENet 仅通过自负相关损失进行优化。另一方面，我们通过探索多个编码特征的多样性和特征的集成策略来提出 EFENet（ 例如 ，组通道均匀加权平均集成和自门加权集成）。多样性由参数较少的编码特征表示，简单的均方误差损失可以实现优越的性能。实验结果证明在准确性和速度方面优于最先进的技术。代码和模型可在以下位置获得： https://github.com/wdzhao123/DENets .