Although deep neural networks (DNNs) have achieved great success in semantic segmentation tasks, it is still challenging for real-time applications. A large number of feature channels, parameters, and floating-point operations make the network sluggish and computationally heavy, which is not desirable for real-time tasks such as robotics and autonomous driving. Most approaches, however, usually sacrifice spatial resolution to achieve inference speed in real time, resulting in poor performance. In this paper, we propose a light-weight stage-pooling semantic segmentation network (SPSSN), which can efficiently reuse the paramount features from early layers at multiple stages, at different spatial resolutions. SPSSN takes input of full resolution 2048×1024 pixels, uses only 1.42 × 10⁶ parameters, yields 69.4% mIoU accuracy without pre-training, and obtains an inference speed of 59 frames/s on the Cityscapes dataset. SPSSN can run directly on mobile devices in real time, due to its light-weight architecture. To demonstrate the effectiveness of the proposed network, we compare our results with those of state-of-the-art networks.

尽管深度神经网络（DNN）在语义分割任务中已经取得了巨大的成功，但对于实时应用程序来说仍然充满挑战。大量的特征通道，参数和浮点运算使网络缓慢且计算繁重，这对于诸如机器人技术和自动驾驶之类的实时任务而言并不理想。但是，大多数方法通常会牺牲空间分辨率来实时获得推理速度，从而导致性能不佳。在本文中，我们提出了一种轻量级的阶段池语义分割网络（SPSSN），该网络可以在不同的空间分辨率下，在多个阶段有效地重用早期层的最重要特征。SPSSN接受全分辨率2048×1024像素的输入，仅使用1.42×10 ⁶参数，无需预先训练即可产生69.4％的mIoU精度，并在Cityscapes数据集上获得59帧/秒的推理速度。由于SPSSN的轻量级架构，它可以直接在移动设备上实时实时运行。为了证明所提议网络的有效性，我们将我们的结果与最新网络的结果进行了比较。