National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610017, China.
Sensors (Basel). 2021 Nov 20;21(22):7730. doi: 10.3390/s21227730.
Semantic segmentation is one of the most active research topics in computer vision with the goal to assign dense semantic labels for all pixels in a given image. In this paper, we introduce HFEN (Hierarchical Feature Extraction Network), a lightweight network to reach a balance between inference speed and segmentation accuracy. Our architecture is based on an encoder-decoder framework. The input images are down-sampled through an efficient encoder to extract multi-layer features. Then the extracted features are fused via a decoder, where the global contextual information and spatial information are aggregated for final segmentations with real-time performance. Extensive experiments have been conducted on two standard benchmarks, Cityscapes and Camvid, where our network achieved superior performance on NVIDIA 2080Ti.
语义分割是计算机视觉中最活跃的研究课题之一，其目标是为给定图像中的所有像素分配密集的语义标签。在本文中，我们介绍了 HFEN（分层特征提取网络），这是一种轻量级网络，可在推理速度和分割精度之间达到平衡。我们的架构基于编解码器框架。输入图像通过高效的编码器进行下采样，以提取多层特征。然后，通过解码器对提取的特征进行融合，在解码器中聚合全局上下文信息和空间信息，以实现具有实时性能的最终分割。我们在两个标准基准数据集 Cityscapes 和 Camvid 上进行了广泛的实验，在 NVIDIA 2080Ti 上，我们的网络实现了卓越的性能。
