论文标题
LRNNET：一个具有有效降低非本地操作的轻加权网络，用于实时语义分割
LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
论文作者
论文摘要
轻加权神经网络的最新发展促进了在资源限制和移动应用程序下进行深度学习的应用。这些应用中的许多应用都需要通过轻度加权网络对语义分割进行实时和有效的预测。本文介绍了一个轻度加权网络，该网络具有有效的降低非本地模块（LRNNET），以进行有效和实时的语义分割。我们提出了重新连接式编码器中的分解卷积块，以实现更轻巧，高效和强大的特征提取。同时，我们提出的减少非本地模块利用空间区域占主导地位的奇异向量来实现降低和更具代表性的非本地特征集成，计算和内存成本要低得多。实验证明了我们在轻巧，速度，计算和准确性之间的较高权衡。在没有其他处理和预处理的情况下，LRNNET在CityScapes测试数据集上仅使用仅使用6.68亿参数的培训和GTX 1080TI卡上的71 fps来实现72.2％MIOU。
The recent development of light-weighted neural networks has promoted the applications of deep learning under resource constraints and mobile applications. Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network. This paper introduces a light-weighted network with an efficient reduced non-local module (LRNNet) for efficient and realtime semantic segmentation. We proposed a factorized convolutional block in ResNet-Style encoder to achieve more lightweighted, efficient and powerful feature extraction. Meanwhile, our proposed reduced non-local module utilizes spatial regional dominant singular vectors to achieve reduced and more representative non-local feature integration with much lower computation and memory cost. Experiments demonstrate our superior trade-off among light-weight, speed, computation and accuracy. Without additional processing and pretraining, LRNNet achieves 72.2% mIoU on Cityscapes test dataset only using the fine annotation data for training with only 0.68M parameters and with 71 FPS on a GTX 1080Ti card.
