论文标题
通过多级异质学习有效的镜像检测
Efficient Mirror Detection via Multi-level Heterogeneous Learning
论文作者
论文摘要
我们提出HETNET（多级\ textbf {het} erogened \ textbf {net}工作），这是一个高效的镜像检测网络。当前的镜像检测方法更多地关注性能而不是效率，从而限制了实时应用程序（例如无人机）。通过在不同级别采用均匀模块的共同设计，他们缺乏效率，这忽略了不同特征级别之间的差异。相反，Hetnet最初通过低级理解（\ textit {e.g。}，强度对比）检测潜在的镜像区域，然后与高级理解（例如上下文不连续性）结合，以最终确定预测。为了执行准确但有效的镜像检测，Hetnet遵循有效的体系结构，该体系结构在不同阶段获取特定信息以检测镜子。我们进一步提出了在HETNET上配备的多向强度对比模块（MIC）和一个反射语义逻辑模块（RSL），分别通过高级理解，通过低级理解和分析场景中的语义逻辑来预测潜在的镜像区域。与最先进的方法相比，HETNET运行664美元$ \％$，并在MAE上的平均性能增益为8.9 $ \％$，IOU上的3.1 $ \％$和2.0 $ \％$ \％$ \％$ $ \％$在两个镜像检测基准上。
We present HetNet (Multi-level \textbf{Het}erogeneous \textbf{Net}work), a highly efficient mirror detection network. Current mirror detection methods focus more on performance than efficiency, limiting the real-time applications (such as drones). Their lack of efficiency is aroused by the common design of adopting homogeneous modules at different levels, which ignores the difference between different levels of features. In contrast, HetNet detects potential mirror regions initially through low-level understandings (\textit{e.g.}, intensity contrasts) and then combines with high-level understandings (contextual discontinuity for instance) to finalize the predictions. To perform accurate yet efficient mirror detection, HetNet follows an effective architecture that obtains specific information at different stages to detect mirrors. We further propose a multi-orientation intensity-based contrasted module (MIC) and a reflection semantic logical module (RSL), equipped on HetNet, to predict potential mirror regions by low-level understandings and analyze semantic logic in scenarios by high-level understandings, respectively. Compared to the state-of-the-art method, HetNet runs 664$\%$ 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.
