We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time applications (such as drones). Their lack of efficiency is aroused by the common design of adopting homogeneous modules at different levels, which ignores the difference between different levels of features. In contrast, HetNet detects potential mirror regions initially through low-level understandings (\textit{e.g.}, intensity contrasts) and then combines with high-level understandings (contextual discontinuity for instance) to finalize the predictions. To perform accurate yet efficient mirror detection, HetNet follows an effective architecture that obtains specific information at different stages to detect mirrors. We further propose a multi-orientation intensity-based contrasted module (MIC) and a reflection semantic logical module (RSL), equipped on HetNet, to predict potential mirror regions by low-level understandings and analyze semantic logic in scenarios by high-level understandings, respectively. Compared to the state-of-the-art method, HetNet runs 664$\%$ faster and draws an average performance gain of 8.9$\%$ on MAE, 3.1$\%$ on IoU, and 2.0$\%$ on F-measure on two mirror detection benchmarks.
翻译:我们提出HetNet(Multi-level level \ textbf{Het}ergenous eurenteous raction net),这是一个高效的镜像探测网络。当前镜像探测方法更侧重于性能而不是效率,限制实时应用(如无人驾驶飞机等),它们缺乏效率的原因是在不同级别采用同质模块的通用设计,忽视不同特性的差异。相比之下,HetNet首先通过低层次理解(\ textit{e.g.},强度对比)来检测潜在的镜像区域,然后与高层次理解(例如通性不连续性)相结合,以最终确定预测。为了进行准确而高效的镜像探测,HetNet遵循一个有效的结构,在不同阶段获得特定信息来检测镜像。我们进一步提议一个基于多方向的强度对比式模块(MIC)和一个映像性逻辑模块(RSL),安装在HetNet上,通过低层次的理解来预测潜在镜像区域,并用高层次理解(例如)美元(直观)和高层次理解,用高层次的美元探测器)来分析假设中的语理逻辑。为了进行准确和高层次理解,分别用高层次的运行和马萨的运行。