Research background
•It can be broadly applied to the fields of augmented reality devices, autonomous driving, and video surveillance. These applications have a high demand for efficient inference speed for fast interaction or response.
在現實應用中，圖像分割常常需要有效的預測和快速的響應。
Recently, the algorithms of real-time semantic segmentation have shown that there are mainly three approaches to accelerate the model.
•try to restrict the input size to reduce the computation complexity by cropping or resizing.
•prune the channels of the network to boost the inference speed especially in the early stages of the base model.
•ENet proposes to drop the last stage of the model in pursuit of an extremely tight framework.
近期論文中有三種方法用以解決圖像分割的快速響應需求，首先，限制輸入大小，這種方法缺點爲會丟失空間細節，尤其是圖像邊界（裁剪和resize）；其次，修剪通道（模型前幾層），缺點是弱化了空間容量，減少精度；最後，減少最後幾層的數量（遺棄下采樣層），缺點是感受野會下降。
（a）減小輸入尺寸和輕量模型（減少前面幾層通道和遺棄後面層）（b）u型網絡，獲得豐富的空間信息，但是是以檢測速度爲代價。（c）本文模型，使用spatial path和context path