This article establishes a baseline for object reflection symmetry detection in natural images by releasing a new benchmark named Sym-PASCAL and proposing an end-to-end deep learning approach for reflection symmetry. Sym-PASCAL spans challenges of multiobjects, object diversity, part invisibility, and clustered backgrounds, which is far beyond those in existing data sets. The end-to-end deep learning approach, referred to as a side-output residual network (SRN), leverages the output residual units (RUs) to fit the errors between the symmetry ground truth and the side outputs of multiple stages of a trunk network. By cascading RUs from deep to shallow, SRN exploits the "flow" of errors along multiple stages to effectively matching object symmetry at different scales and suppress the clustered backgrounds. SRN is interpreted as a boosting-like algorithm, which assembles features using RUs during network forward and backward propagations. SRN is further upgraded to a multitask SRN (MT-SRN) for joint symmetry and edge detection, demonstrating its generality to image-to-mask learning tasks. Experimental results verify that the Sym-PASCAL benchmark is challenging related to real-world images, SRN achieves state-of-the-art performance, and MT-SRN has the capability to simultaneously predict edge and symmetry mask without loss of performance.

中文翻译：

---

SRN：用于对象反射对称检测及其他方面的侧输出残差网络。

本文通过发布名为 Sym-PASCAL 的新基准并提出一种端到端的反射对称性深度学习方法，为自然图像中的对象反射对称性检测建立了基线。Sym-PASCAL 跨越了多对象、对象多样性、部分不可见性和聚类背景的挑战，这远远超出了现有数据集中的挑战。端到端深度学习方法，称为侧输出残差网络 (SRN)，利用输出残差单元 (RU) 来拟合对称地面实况和主干多个阶段的侧输出之间的误差网络。通过从深到浅级联 RU，SRN 利用沿多个阶段的错误“流”来有效匹配不同尺度的对象对称性并抑制聚类背景。SRN 被解释为一种类似 boosting 的算法，它在网络前向和后向传播期间使用 RU 组合特征。SRN 进一步升级为多任务 SRN (MT-SRN)，用于联合对称和边缘检测，展示了其对图像到掩模学习任务的通用性。实验结果验证了 Sym-PASCAL 基准在与真实世界图像相关的挑战，SRN 实现了最先进的性能，并且 MT-SRN 能够同时预测边缘和对称掩码而不会损失性能。